© 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. 5209
    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
    éĩįéĩį
    -0.24
    feld
    -0.24
    grav
    -0.23
     mitt
    -0.23
     Ook
    -0.23
    ä¸įè§ģ
    -0.23
     css
    -0.23
     layers
    -0.23
    追究
    -0.23
    áp
    -0.23
    POSITIVE LOGITS
    次æķ°
    0.26
    ä¹IJè§Ĥ
    0.26
     ìĸ¼ë§ĪëĤĺ
    0.25
     quiet
    0.25
    ç²Ł
    0.25
     "/",
    0.25
     mart
    0.25
     tri
    0.24
    jen
    0.23
    knife
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.