© 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. 5288
    Prev
    Next
    INDEX
    Explanations

    Punctuation and special characters

    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
     Za
    -0.26
    otti
    -0.25
    боÑĤ
    -0.25
    師
    -0.24
    ATORY
    -0.24
     Kom
    -0.23
    pais
    -0.23
    æĪIJ为ä¸Ģ个
    -0.23
    ountain
    -0.23
    ç³ł
    -0.23
    POSITIVE LOGITS
    ilon
    0.26
    gettext
    0.24
    odate
    0.24
     mÄĻżczyzn
    0.23
    mlin
    0.23
     uczniów
    0.23
    äºİ
    0.23
     disput
    0.23
    ä¹Łä¸įä¾ĭå¤ĸ
    0.23
    BB
    0.23
    Activations Density 0.004%

    No Known Activations