© 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. 163427
    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
    裾
    -0.26
     "<?
    -0.26
    @example
    -0.26
    åı¯ä»¥æł¹æį®
    -0.25
     rés
    -0.25
    _flow
    -0.25
     '<?
    -0.24
    çľ¼è§Ĵ
    -0.24
     NGX
    -0.23
    æĻºåķĨ
    -0.23
    POSITIVE LOGITS
    èĭŀ
    0.25
    ç«ĭä½ĵ
    0.24
    blas
    0.24
    ÃŃ
    0.23
    explo
    0.23
    æ³ķå¾ĭè§Ħå®ļ
    0.23
     Spears
    0.23
    cast
    0.23
    emen
    0.23
     lab
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.