© 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. 54548
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    idis
    -0.29
    çĦ¶åIJİ
    -0.25
    dbe
    -0.25
    verbosity
    -0.25
    dfd
    -0.25
     merry
    -0.24
     nic
    -0.24
    åľ°éĿ¢
    -0.24
    IFY
    -0.24
    /board
    -0.24
    POSITIVE LOGITS
    ledged
    0.30
    æĥħåĨµä¸ĭ
    0.26
    pute
    0.26
    нÑı
    0.26
    ä¸Ģè§Ī
    0.26
    onald
    0.26
    precated
    0.24
    toFloat
    0.23
    éªĸ
    0.23
    į°
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.