© 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. 163121
    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
     today
    -0.30
     Passed
    -0.28
    esModule
    -0.27
    èµ¢å¾ĹäºĨ
    -0.27
     ÑģегоднÑı
    -0.27
    ä»Ĭ天
    -0.26
     hoje
    -0.26
    orsche
    -0.26
     hoy
    -0.25
     hôm
    -0.25
    POSITIVE LOGITS
    _same
    0.28
    å®Įç¾İ
    0.26
    涯
    0.25
    æĭ£
    0.25
    åijĪçİ°
    0.25
    Adjacent
    0.25
    Frozen
    0.25
    cum
    0.24
    _inactive
    0.24
     CJ
    0.24
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.