© 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. 5787
    Prev
    Next
    INDEX
    Explanations

    Negative situations

    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
    åĬŁåĬ³
    -0.29
    rex
    -0.28
    åĬŁ
    -0.26
    acos
    -0.26
    Pan
    -0.25
    JS
    -0.25
    ä¾ĭå¤ĸ
    -0.24
    ä¹Łåľ¨
    -0.24
     RELEASE
    -0.24
    an
    -0.24
    POSITIVE LOGITS
     Bernardino
    0.29
     storm
    0.28
    主人
    0.27
    ogne
    0.26
     orig
    0.25
    é£İæļ´
    0.25
    .gnu
    0.25
    §Ãĥ
    0.25
    insky
    0.25
    Ĭ¶
    0.24
    Activations Density 0.020%

    No Known Activations