© 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. 33-TRANSCODER-HP
    7. 52796
    Prev
    Next
    INDEX
    Explanations

    using/use

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     reprodu
    -0.27
    Bes
    -0.26
    人家
    -0.26
    weather
    -0.26
    contract
    -0.26
    åĢĴæĺ¯
    -0.25
    Remaining
    -0.25
     profits
    -0.25
    missing
    -0.25
    .GetCurrent
    -0.24
    POSITIVE LOGITS
    éĩİ
    0.27
    ç¡IJ
    0.26
    ozy
    0.26
    (sym
    0.26
     ^=
    0.26
    åħ³éĶ®åŃĹ
    0.26
    iena
    0.25
    виз
    0.25
    ñas
    0.25
    ONSE
    0.24
    Activations Density 0.247%

    No Known Activations