© 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. 14-TRANSCODER-HP
    7. 40303
    Prev
    Next
    INDEX
    Explanations

    categories and properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»İæľª
    -0.27
     kitten
    -0.26
    å¡«åĨĻ
    -0.25
    çļĦä¸ĢéĿ¢
    -0.25
    Smoke
    -0.25
    éĵ¾
    -0.24
    edian
    -0.24
    cm
    -0.23
    kaar
    -0.23
    èĮ§
    -0.23
    POSITIVE LOGITS
    furt
    0.32
     Clo
    0.30
    uos
    0.27
    icha
    0.27
     crashing
    0.26
    lesh
    0.25
    .rawValue
    0.25
    ãģļ
    0.25
     ..."↵
    0.25
    isha
    0.24
    Activations Density 0.309%

    No Known Activations