© 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. 5766
    Prev
    Next
    INDEX
    Explanations

    Historical records

    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
    çļĦè¿ĽæŃ¥
    -0.27
    æ²±
    -0.27
    称ä¹ĭ
    -0.27
    为æ°ij
    -0.25
    æłĵ
    -0.24
    驺
    -0.24
    obox
    -0.24
    stk
    -0.24
    åĽ´
    -0.23
    ัส
    -0.23
    POSITIVE LOGITS
    ercul
    0.28
    ospels
    0.25
    /xhtml
    0.25
     certo
    0.24
     assumes
    0.24
     assumption
    0.24
    ä¸Ģå®ļ
    0.23
    erset
    0.23
    æľīæľºç»ĵåIJĪ
    0.23
    /latest
    0.23
    Activations Density 0.011%

    No Known Activations