© 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. 65669
    Prev
    Next
    INDEX
    Explanations

    shallow/superficial

    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
     nhiễ
    -0.08
     triples
    -0.08
     Но
    -0.07
     transforms
    -0.07
     diffs
    -0.07
     ]);↵↵
    -0.07
     Exceptions
    -0.06
    .ViewHolder
    -0.06
    asts
    -0.06
     affine
    -0.06
    POSITIVE LOGITS
     slamming
    0.07
    /column
    0.07
    套路
    0.07
    .Binding
    0.07
    يار
    0.07
    选择
    0.06
    赛道
    0.06
    كاف
    0.06
    私立
    0.06
    /plugin
    0.06
    Activations Density 0.009%

    No Known Activations