© 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. 39960
    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
     Tradable
    -0.30
    :start
    -0.28
    ioned
    -0.27
    asta
    -0.27
    _pas
    -0.26
    亲åıĭ
    -0.26
    èĬ±å¼Ģ
    -0.26
     watcher
    -0.26
    触åĬ¨
    -0.26
    å¼Ģ
    -0.25
    POSITIVE LOGITS
    é»ĥ
    0.26
    ä¸ŃåĽ½å¸Ĥåľº
    0.25
    /he
    0.24
    Configuration
    0.24
    _course
    0.24
     Japanese
    0.23
    æĹłç©·
    0.23
    ingham
    0.23
     measures
    0.23
    åĮ»çĸĹä¿ĿéĻ©
    0.23
    Activations Density 0.369%

    No Known Activations

    This feature has no known activations.