© 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. 19-TRANSCODER-HP
    7. 9343
    Prev
    Next
    INDEX
    Explanations

    Code snippets/programming discussions

    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
     Ref
    -0.26
     ref
    -0.25
    owler
    -0.25
    Ref
    -0.25
    _REF
    -0.24
    idd
    -0.24
    icked
    -0.24
     Ideal
    -0.24
    Descri
    -0.23
    .Ref
    -0.23
    POSITIVE LOGITS
    beck
    0.26
    INGER
    0.25
    zilla
    0.25
    åŃĿ
    0.25
    MAS
    0.24
    绾
    0.23
    stå
    0.23
    htags
    0.23
     blinds
    0.23
     crossings
    0.23
    Activations Density 0.023%

    No Known Activations