© 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. 18-TRANSCODER-HP
    7. 89244
    Prev
    Next
    INDEX
    Explanations

    Id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tablename
    -0.28
     inertia
    -0.27
     culture
    -0.27
    {j
    -0.26
    ltra
    -0.26
    Culture
    -0.26
    ohana
    -0.26
    tables
    -0.25
     Lv
    -0.25
     Alv
    -0.24
    POSITIVE LOGITS
    æµģåIJij
    0.28
    éĻ¢éĻ¢å£«
    0.27
    ington
    0.26
    çªĹå¸ĺ
    0.26
    IFDEF
    0.26
    heit
    0.25
    ä¾Ľ
    0.25
    ipsis
    0.24
    icone
    0.24
    icht
    0.24
    Activations Density 1.684%

    No Known Activations