© 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. 162466
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    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
    oga
    -0.27
    antic
    -0.27
    第ä¸ĥ
    -0.27
    ago
    -0.26
    FK
    -0.25
    æ°´æĻ¶
    -0.24
    itecture
    -0.24
    èĻŀ
    -0.24
    çļĦ人éĥ½
    -0.24
    .Slice
    -0.24
    POSITIVE LOGITS
    whereIn
    0.26
     bast
    0.25
    abee
    0.25
    çļĦä¾ĭåŃIJ
    0.25
    åħ¸åŀĭæ¡Īä¾ĭ
    0.25
    /Resources
    0.24
    æĪ¬
    0.24
    asti
    0.24
    larımız
    0.24
    bast
    0.24
    Activations Density 0.028%

    No Known Activations