© 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. 40297
    Prev
    Next
    INDEX
    Explanations

    antibiotics and bacteria

    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
    踵
    -0.26
    éĹ¨æ§Ľ
    -0.26
    illion
    -0.24
    agon
    -0.24
    (Config
    -0.24
    æĢł
    -0.24
    模仿
    -0.23
    解èĦ±
    -0.23
     attic
    -0.23
    åķĨåľĪ
    -0.23
    POSITIVE LOGITS
     fav
    0.45
    fav
    0.43
     favor
    0.42
     favour
    0.40
    yne
    0.37
    favor
    0.36
    favorite
    0.34
    irc
    0.34
     favored
    0.34
    a
    0.33
    Activations Density 0.035%

    No Known Activations