© 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. 163824
    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
    åŃĶ
    -0.26
    ç©¿æĪ´
    -0.25
    ât
    -0.25
    ç³Ł
    -0.24
    ä¸ķ
    -0.24
    aramel
    -0.24
    ilers
    -0.24
    à¸Ńà¸ģ
    -0.24
    arbon
    -0.24
     individual
    -0.24
    POSITIVE LOGITS
    anni
    0.28
    chi
    0.28
    éĴ¿
    0.26
    Chi
    0.26
    åĽłä¸ºæĪij们
    0.26
    åIJ½
    0.25
    iens
    0.24
    :Int
    0.24
    æĽĻåħī
    0.24
    usz
    0.24
    Activations Density 0.173%

    No Known Activations

    This feature has no known activations.