© 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. 43132
    Prev
    Next
    INDEX
    Explanations

    say "start" or "look"

    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
     interiors
    -0.31
    ndon
    -0.29
    ç«Ļ
    -0.29
    .internal
    -0.27
    YST
    -0.26
     Ster
    -0.26
    ÑģÑĤан
    -0.26
    ÑģÑĤвÑĥ
    -0.26
    AVIS
    -0.26
    sticks
    -0.26
    POSITIVE LOGITS
    nk
    0.28
     fall
    0.28
     tie
    0.26
    ffa
    0.26
     Fall
    0.25
     jump
    0.24
    åİŁæłĩé¢ĺ
    0.24
     tt
    0.24
    ility
    0.24
    çĤ¹åĩ»æŁ¥çľĭ
    0.24
    Activations Density 0.002%

    No Known Activations