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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 345
    Prev
    Next
    INDEX
    Explanations

    hide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSMutable
    -0.07
    出资
    -0.07
    achi
    -0.07
    戋
    -0.07
    .Next
    -0.07
     Emb
    -0.06
     planned
    -0.06
     nonlinear
    -0.06
     kk
    -0.06
     wcs
    -0.06
    POSITIVE LOGITS
     inhibit
    0.08
    تين
    0.07
    大批
    0.07
    的记忆
    0.07
    |R
    0.07
     sticking
    0.07
     falsehood
    0.07
    密碼
    0.07
     incorporation
    0.07
    BackingField
    0.07
    Activations Density 0.007%

    No Known Activations