© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161867
    Prev
    Next
    INDEX
    Explanations

    Questions and essay excerpts

    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
    Flo
    -0.27
     Flo
    -0.26
     flo
    -0.26
    CACHE
    -0.26
    tx
    -0.26
    Var
    -0.26
     StringTokenizer
    -0.26
     Already
    -0.25
    è£ħå¤ĩ
    -0.24
    .toObject
    -0.24
    POSITIVE LOGITS
    æ·±åĪ»çļĦ
    0.32
     attributed
    0.32
     numbering
    0.29
    æ·±åĪ»
    0.28
    licing
    0.26
    aman
    0.25
    æĴ°åĨĻ
    0.25
    shed
    0.25
    ä»ĸ说
    0.24
    书åĨĻ
    0.24
    Activations Density 0.002%

    No Known Activations