© 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. 27-TRANSCODER-HP
    7. 9203
    Prev
    Next
    INDEX
    Explanations

    Little

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubar
    -0.33
    SCI
    -0.29
    edb
    -0.27
    dives
    -0.27
    æħ¢æħ¢
    -0.27
     Isles
    -0.26
    cka
    -0.26
    å¿Į
    -0.26
     ub
    -0.26
     sola
    -0.25
    POSITIVE LOGITS
    è¿Ń代
    0.27
    æ¼Ķèīº
    0.26
    .liferay
    0.26
     paren
    0.25
    Iter
    0.25
    lds
    0.24
    éŀ²
    0.24
     gag
    0.24
    erald
    0.24
    лок
    0.24
    Activations Density 0.156%

    No Known Activations