© 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. 163329
    Prev
    Next
    INDEX
    Explanations

    Snippets of random text/titles

    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
    åıijå±ķè§ĦåĪĴ
    -0.28
    nı
    -0.26
    eled
    -0.26
    ä¸į说
    -0.25
    assed
    -0.25
    endcode
    -0.25
    人æŃ»äº¡
    -0.24
     Minimal
    -0.24
    emax
    -0.24
    å®ĺ宣
    -0.24
    POSITIVE LOGITS
    线
    0.28
    ibil
    0.27
    pragma
    0.27
     Ago
    0.26
    rÄĻ
    0.24
    è¿Ľè¡Įåħ¨éĿ¢
    0.24
    éģĤ
    0.24
     اÙĦجÙħع
    0.23
     Entire
    0.23
    ราà¸ĩ
    0.23
    Activations Density 0.003%

    No Known Activations