© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 3408
    Prev
    Next
    INDEX
    Explanations

    display

    np_max-act · gemini-2.0-flash

    CSS layout and positioning declarations, especially lines setting display modes and vertical/vertical-like alignment behavior.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﳊ
    -0.07
    esign
    -0.06
    Design
    -0.06
    คร
    -0.06
     vscode
    -0.06
     tạo
    -0.06
    TYPES
    -0.06
     simpl
    -0.06
     codigo
    -0.06
    Thr
    -0.06
    POSITIVE LOGITS
    anner
    0.08
    物流公司
    0.07
     Cindy
    0.07
    _characters
    0.07
     italiane
    0.07
     unreachable
    0.06
    .role
    0.06
    ам
    0.06
    文化传播
    0.06
     aquel
    0.06
    Activations Density 0.008%

    No Known Activations