© 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. 161779
    Prev
    Next
    INDEX
    Explanations

    evidence and cases

    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
    åIJĦ个æĸ¹éĿ¢
    -0.29
    vang
    -0.29
    SCREEN
    -0.28
    indi
    -0.27
    纵横
    -0.27
    ĶåĽŀ
    -0.27
    èĩªèIJ¥
    -0.26
    rowser
    -0.26
    soever
    -0.26
     Sidebar
    -0.25
    POSITIVE LOGITS
     confirming
    0.29
    SES
    0.27
    sit
    0.26
    è¯ģæĺİ
    0.26
     over
    0.25
    uez
    0.25
    ses
    0.25
    :
    0.25
     proving
    0.25
    .ld
    0.25
    Activations Density 0.014%

    No Known Activations