© 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. 5461
    Prev
    Next
    INDEX
    Explanations

    Code, categories, or dates

    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
    afen
    -0.28
    èºIJ
    -0.27
    .CONNECT
    -0.26
    PLUGIN
    -0.24
    inton
    -0.24
    eel
    -0.24
    æľ¬æ¬¡æ´»åĬ¨
    -0.24
     Battlefield
    -0.24
     sca
    -0.24
    eren
    -0.24
    POSITIVE LOGITS
     similarly
    0.33
    ä¹Łæĺ¯å¦ĤæѤ
    0.30
     Similarly
    0.30
     likewise
    0.28
     Likewise
    0.28
    ä¹Łä¸įä¾ĭå¤ĸ
    0.27
     correspond
    0.26
    åīįèĢħ
    0.26
     perv
    0.25
    Similarly
    0.25
    Activations Density 0.467%

    No Known Activations