© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26352
    Prev
    Next
    INDEX
    Explanations

    will

    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
     بالنسبة
    -0.07
     yytype
    -0.07
    뀜
    -0.06
     Take
    -0.06
     kém
    -0.06
    ┲
    -0.06
    ================
    -0.06
     בעיני
    -0.06
    数控
    -0.06
    思い
    -0.06
    POSITIVE LOGITS
    _chip
    0.08
     안
    0.07
    兼容
    0.07
    팍
    0.07
    内分泌
    0.07
     radius
    0.07
    FEATURE
    0.07
    _can
    0.07
     Bip
    0.07
    _guide
    0.07
    Activations Density 0.207%

    No Known Activations