© 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. 5262
    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
    pls
    -0.28
     IEntity
    -0.26
    zÄĻ
    -0.26
    azioni
    -0.25
    æĬ¹
    -0.25
    认è¯ĨåĪ°
    -0.25
    ream
    -0.24
    大æ¦Ĥæĺ¯
    -0.24
    xit
    -0.23
    æĽ³
    -0.23
    POSITIVE LOGITS
     dece
    0.26
    venes
    0.25
     proced
    0.24
     defe
    0.24
    åĪĨåĮĸ
    0.24
    (Log
    0.23
    Touches
    0.23
    ç§ģä¸ĭ
    0.23
    strar
    0.23
    awns
    0.23
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.