© 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. 163837
    Prev
    Next
    INDEX
    Explanations

    by

    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
    itizer
    -0.29
    iors
    -0.29
     year
    -0.26
    omer
    -0.26
    -year
    -0.26
     specificity
    -0.26
     mystery
    -0.26
    anmar
    -0.25
    ategor
    -0.25
     mysteries
    -0.25
    POSITIVE LOGITS
     Central
    0.31
    Central
    0.28
    ä¸Ń央
    0.28
     Hyde
    0.27
     central
    0.27
     National
    0.26
    éļ¶å±ŀäºİ
    0.26
     Ext
    0.26
     Discount
    0.25
    house
    0.25
    Activations Density 0.007%

    No Known Activations