© 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
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 163785
    Prev
    Next
    INDEX
    Explanations

    period

    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
    åŁİå¸Ĥ建设
    -0.27
    oner
    -0.26
    _QMARK
    -0.25
    __,↵
    -0.24
    iones
    -0.24
     *__
    -0.24
    "\↵
    -0.23
    äºĨä¸Ģ
    -0.23
    /__
    -0.23
    äºĨ好åĩł
    -0.23
    POSITIVE LOGITS
    ç®Ĺ
    0.30
    å¢Ł
    0.27
    åıĹ
    0.27
    为æŃ¤
    0.26
    éĩijåĪļ
    0.26
    cade
    0.25
    arat
    0.24
    vn
    0.24
    æīĢä»¥åľ¨
    0.24
    辩è¯ģ
    0.24
    Activations Density 0.017%

    No Known Activations