© 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. 41726
    Prev
    Next
    INDEX
    Explanations

    Y / y

    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®Ŀè´µçļĦ
    -0.31
    è´µ
    -0.29
     Äij
    -0.28
    @\
    -0.28
     Qu
    -0.27
    ivated
    -0.27
     Civ
    -0.26
    (off
    -0.26
    arto
    -0.25
    bv
    -0.25
    POSITIVE LOGITS
     slam
    0.30
    è¡Į使
    0.28
    kah
    0.28
    æķ´å½¢
    0.28
    icter
    0.27
     Waist
    0.25
     rollers
    0.24
    anes
    0.24
     slip
    0.24
    ellig
    0.23
    Activations Density 0.003%

    No Known Activations