© 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. 162474
    Prev
    Next
    INDEX
    Explanations

    reviews and ratings

    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
    çķ¥
    -0.30
    çľĭä¸Ģçľĭ
    -0.30
    绣ä¸Ģ
    -0.29
     unsur
    -0.27
    tein
    -0.27
    aes
    -0.26
     measurable
    -0.26
    éħIJ
    -0.25
     Unified
    -0.25
    æ·¼
    -0.24
    POSITIVE LOGITS
    éģ½
    0.29
    èĦijè¢ĭ
    0.27
     Matter
    0.27
    èĥĥåı£
    0.27
    wnd
    0.26
     yüz
    0.25
    æį¢æĿ¥
    0.25
    èĦijåŃIJ
    0.25
    .twig
    0.25
    ç§ij缮
    0.24
    Activations Density 0.002%

    No Known Activations