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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23832
    Prev
    Next
    INDEX
    Explanations

    Sun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umer
    -0.28
    PRESS
    -0.27
    erval
    -0.27
    æĸ¹å¼ıè¿Ľè¡Į
    -0.26
     Stopwatch
    -0.26
    pecting
    -0.25
    press
    -0.24
    å¼ĩ
    -0.24
    æĺ¯ä»¥
    -0.24
     NDP
    -0.23
    POSITIVE LOGITS
    reib
    0.25
     prem
    0.25
    handler
    0.25
    bbb
    0.25
     cracked
    0.25
    æĹ¢çĦ¶
    0.24
    /gen
    0.24
    emin
    0.23
     Rein
    0.23
    æīĢå±ŀ
    0.23
    Activations Density 0.000%

    No Known Activations