© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7532
    Prev
    Next
    INDEX
    Explanations

    Statistics and parenthesis symbols

    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
    ооÑĢÑĥж
    -0.29
    éĬ·
    -0.28
    anford
    -0.27
     revers
    -0.26
     dresser
    -0.25
    becue
    -0.25
     grav
    -0.25
    osterone
    -0.24
    秤
    -0.24
    galement
    -0.24
    POSITIVE LOGITS
     untouched
    0.29
    室åĨħ
    0.27
    èĤĮèĤ¤
    0.26
    "_
    0.26
    æĪª
    0.25
    (_
    0.25
     unic
    0.25
     _(
    0.24
     comet
    0.24
     aged
    0.24
    Activations Density 0.171%

    No Known Activations