© 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. 162442
    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
    .fe
    -0.30
     fe
    -0.28
    æķĻ
    -0.27
    ä¸ĩ家
    -0.26
     hass
    -0.25
    æĽ²æĬĺ
    -0.25
     Fe
    -0.24
    æļ®ãĤī
    -0.23
    пов
    -0.23
     rond
    -0.23
    POSITIVE LOGITS
    饷
    0.29
    纪æ£Ģ
    0.26
    upal
    0.26
    æŶéĹ´
    0.25
    绳
    0.24
    Action
    0.24
     fut
    0.24
    _SRV
    0.24
    deaux
    0.24
    åħ´èµ·
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.