© 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. 163815
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ»´
    -0.26
    èĤ¥
    -0.25
    è´Ŀ
    -0.25
    éĶĢ
    -0.24
    cons
    -0.24
    _subplot
    -0.24
    æĹłäºº
    -0.23
     leuk
    -0.23
     QModelIndex
    -0.23
    å³°ä¼ļ
    -0.23
    POSITIVE LOGITS
    turned
    0.30
    аниÑİ
    0.24
     Worst
    0.24
     refuses
    0.24
     refusing
    0.24
    ZE
    0.24
     ØŃÙĤ
    0.23
    éĶ¢
    0.23
     Casting
    0.23
     casting
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.