© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5759
    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
    ind
    -0.29
    over
    -0.28
    è¦ģçĤ¹
    -0.27
    containers
    -0.26
    ingle
    -0.26
     conv
    -0.26
    je
    -0.25
    ingen
    -0.25
    йÑĤе
    -0.24
    plates
    -0.24
    POSITIVE LOGITS
    (boost
    0.31
    criptor
    0.29
    ibu
    0.25
    iban
    0.25
    橹
    0.24
    ç½ij讯
    0.24
    dbo
    0.24
    .simps
    0.23
     noble
    0.23
     retros
    0.23
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.