© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 41731
    Prev
    Next
    INDEX
    Explanations

    language, words or anagrams

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ;)
    -0.07
    欄
    -0.07
    ;)
    -0.07
     Infos
    -0.07
    .network
    -0.07
    未能
    -0.07
     العلاقة
    -0.07
     blinded
    -0.07
    ificate
    -0.07
    ardown
    -0.07
    POSITIVE LOGITS
     +↵
    0.07
    (_
    0.07
     unconditional
    0.07
    $str
    0.07
    TouchableOpacity
    0.07
    embedding
    0.07
    东盟
    0.07
    쫑
    0.07
    [@
    0.06
    鲇
    0.06
    Activations Density 0.127%

    No Known Activations