© 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. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -pres
    -0.24
     GG
    -0.24
    -wrap
    -0.24
    iss
    -0.23
     rá
    -0.23
     acid
    -0.23
    è·Łä»ĸ
    -0.23
    éħ¸
    -0.23
    oul
    -0.23
     issuance
    -0.23
    POSITIVE LOGITS
    ä¹ĭéĻħ
    0.35
    è·³åĩº
    0.26
    ç®Ĺ
    0.25
    èĢģ大
    0.25
    ä¸įå°½
    0.24
    ãģĵãģ¨ãģĮãģ§ãģįãĤĭ
    0.24
    à¸Ĺาà¸Ļ
    0.24
    个åĪ«
    0.24
    _representation
    0.24
    (filepath
    0.23
    Activations Density 10.275%

    No Known Activations

    This feature has no known activations.