© 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. 42220
    Prev
    Next
    INDEX
    Explanations

    legal or hearings

    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
     wur
    -0.29
     Independ
    -0.27
    .handleError
    -0.27
    åĩ¡æľ¬ç½ij
    -0.26
    idy
    -0.26
     hoax
    -0.25
    į°
    -0.25
    damn
    -0.25
    idend
    -0.24
    бÑĥд
    -0.24
    POSITIVE LOGITS
     st
    0.29
    ä¸įåıĬ
    0.28
    uled
    0.27
    Ar
    0.25
    kar
    0.25
    arring
    0.25
    èĥĥ
    0.25
    ga
    0.25
    -inf
    0.25
    ufen
    0.25
    Activations Density 0.000%

    No Known Activations