© 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. 39380
    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
    ewise
    -0.26
    èĢĥ
    -0.25
    ä¸ĢæĬĬ
    -0.25
    èºģ
    -0.24
     mods
    -0.24
    å¨ĺ
    -0.24
    rijk
    -0.24
    acher
    -0.24
    uc
    -0.24
    èĢĥåľº
    -0.24
    POSITIVE LOGITS
    izard
    0.28
     ListTile
    0.26
     vois
    0.26
    xFD
    0.26
    xdf
    0.24
     дог
    0.24
    ä¸Ģ个å¤ļ
    0.24
    Ø·ÙĬ
    0.24
    ä¹¾åĿ¤
    0.24
     grátis
    0.24
    Activations Density 0.978%

    No Known Activations

    This feature has no known activations.