© 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. 32-TRANSCODER-HP
    7. 42903
    Prev
    Next
    INDEX
    Explanations

    Location or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·´å·´
    -0.27
    zel
    -0.27
    marks
    -0.27
    é«ĺ涨
    -0.26
    quat
    -0.26
    çĥŃ
    -0.26
    è¿Ļä¸Ģå¹´
    -0.25
    çĵ£
    -0.24
    sez
    -0.24
    é¢ij
    -0.24
    POSITIVE LOGITS
    åĮ¡
    0.28
     Merr
    0.27
    apel
    0.25
    ^^^^
    0.25
    åħ»èĢģ
    0.24
    ewood
    0.24
     pen
    0.24
    éĿł
    0.24
    amespace
    0.24
    ICODE
    0.24
    Activations Density 0.002%

    No Known Activations