© 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. 162651
    Prev
    Next
    INDEX
    Explanations

    Subscriptions

    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
    è¿Ļä¸Ģå¹´
    -0.26
    typeparam
    -0.26
     tit
    -0.25
    éĤ£å¤©
    -0.25
    ä¼ijåģĩ
    -0.24
    eted
    -0.24
    ulla
    -0.24
    廪
    -0.23
    rette
    -0.23
    mui
    -0.23
    POSITIVE LOGITS
    太å°ij
    0.29
     æĸ
    0.26
    .terminate
    0.25
    è¿ĩå¤ļ
    0.24
     costing
    0.24
     Forgotten
    0.24
     {_
    0.24
    CSR
    0.23
    太è¿ĩ
    0.23
    AWN
    0.23
    Activations Density 0.008%

    No Known Activations