© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40465
    Prev
    Next
    INDEX
    Explanations

    h

    np_max-act-logits · gemini-2.0-flash
    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
     hell
    -0.26
    ä¸ĢæĹ¥
    -0.25
    held
    -0.25
    SHOP
    -0.24
    holding
    -0.24
    dra
    -0.23
     compass
    -0.23
     once
    -0.23
     fractions
    -0.23
    æĥ³åİ»
    -0.23
    POSITIVE LOGITS
     URL
    0.33
    confirmed
    0.28
    "url
    0.26
    è¾Ľåĭ¤
    0.26
    ateful
    0.26
    æĸ°éĹ»åıijå¸ĥ
    0.25
    é¢Ĩ导人
    0.25
    0.24
    çĶ±ä¸ŃåĽ½
    0.24
    ATER
    0.24
    Activations Density 35.002%

    No Known Activations