© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95159
    Prev
    Next
    INDEX
    Explanations

    colon and coloproctology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Lens
    -0.29
    eling
    -0.29
     grown
    -0.29
    LICENSE
    -0.28
     Lip
    -0.28
    plug
    -0.27
    LS
    -0.27
    omen
    -0.26
     lip
    -0.26
    adero
    -0.26
    POSITIVE LOGITS
     sweeps
    0.27
    cm
    0.27
     Te
    0.26
     swept
    0.26
     celebrated
    0.26
    изаÑĤоÑĢ
    0.25
    ApplicationBuilder
    0.25
    é¢ij
    0.25
    æ³°å®ī
    0.24
    .checked
    0.24
    Activations Density 0.913%

    No Known Activations