© 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. 163320
    Prev
    Next
    INDEX
    Explanations

    beginnings of documents

    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
     daily
    -0.30
    daily
    -0.28
    æ¯ıæĹ¥
    -0.27
    æĽ´ä½İ
    -0.27
    Daily
    -0.27
     Daily
    -0.27
    éĹ¨æ§Ľ
    -0.26
    ISON
    -0.25
    èĬ¸
    -0.25
    æĪªæŃ¢
    -0.25
    POSITIVE LOGITS
    å¥ĩ
    0.30
    åģ¶
    0.29
     Middle
    0.28
     odd
    0.27
    CardBody
    0.26
     feu
    0.26
     license
    0.26
    .contacts
    0.25
    _odd
    0.25
     LICENSE
    0.25
    Activations Density 0.000%

    No Known Activations