© 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. 23-TRANSCODER-HP
    7. 163229
    Prev
    Next
    INDEX
    Explanations

    Code and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nees
    -0.28
    èĢĮåIJİ
    -0.28
    ãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    -0.27
     Zuk
    -0.27
    utos
    -0.26
    dens
    -0.25
     afterwards
    -0.25
    ãģĵãģ¨ãģĮãģĤãĤĬãģ¾ãģĻ
    -0.25
    _pars
    -0.25
    incerely
    -0.25
    POSITIVE LOGITS
    çļĸ
    0.26
    å®īæ£Ģ
    0.26
    è°±
    0.26
    çŃīæĸ¹éĿ¢çļĦ
    0.26
    ä¸Ĭ
    0.25
    åĪ¤
    0.24
    æĻ®æ³ķ
    0.24
     originated
    0.24
    Outer
    0.24
    std
    0.23
    Activations Density 0.102%

    No Known Activations