© 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. 19-TRANSCODER-HP
    7. 8330
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èŀĤ
    -0.26
    usty
    -0.26
    _rat
    -0.25
    sweet
    -0.25
    (feed
    -0.25
    èĢĮæĺ¯
    -0.24
    绵
    -0.24
    .Feed
    -0.23
    olation
    -0.23
    apult
    -0.23
    POSITIVE LOGITS
    bef
    0.30
    lie
    0.28
    alia
    0.28
     Tes
    0.24
    ima
    0.24
    lé
    0.24
    .#
    0.24
    åĽłä¸ºæĪij
    0.23
    faf
    0.23
    奴
    0.23
    Activations Density 0.872%

    No Known Activations

    This feature has no known activations.