© 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. 19-TRANSCODER-HP
    7. 8552
    Prev
    Next
    INDEX
    Explanations

    Anatomical/directional suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stump
    -0.28
    vice
    -0.28
    æł·çļĦ
    -0.27
    Round
    -0.26
     odpowied
    -0.25
    ERIC
    -0.25
    éļıæīĭ
    -0.25
    ecd
    -0.24
    ers
    -0.24
    åħ·æľīèī¯å¥½
    -0.24
    POSITIVE LOGITS
    ñas
    0.30
    .xhtml
    0.29
    éĥ¨
    0.25
    orum
    0.25
    phet
    0.24
    éĥ¨å§Ķ
    0.24
     segregation
    0.24
    obia
    0.23
    structuring
    0.23
     pard
    0.23
    Activations Density 0.413%

    No Known Activations