© 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. 162591
    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
    æľªæĿ¥çļĦ
    -0.26
     Pist
    -0.26
    ç¢ĵ
    -0.26
    HELL
    -0.25
    æłĹ
    -0.25
    gent
    -0.24
    gene
    -0.24
    ç½Ĺæĸ¯
    -0.24
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.24
    éĻĪåĪĹ
    -0.24
    POSITIVE LOGITS
    assage
    0.28
    ä¼łçIJĥ
    0.27
    .DEFINE
    0.26
     straight
    0.26
    ublic
    0.26
    sitemap
    0.25
    áz
    0.25
     Ủ
    0.25
     transfer
    0.24
    à´´
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.