© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 90049
    Prev
    Next
    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _repeat
    -0.26
    åĿª
    -0.24
    Ø·ÙĨ
    -0.24
    аÑĤÑĥÑĢ
    -0.24
     addTarget
    -0.24
    æĺİç¡®
    -0.23
    :Event
    -0.23
    æ°¸ä¸į
    -0.23
    ixe
    -0.23
    æĺİæĻ°
    -0.23
    POSITIVE LOGITS
    代价
    0.28
    æ´ĭæ´ĭ
    0.27
    spread
    0.25
     complement
    0.25
     Vect
    0.25
     compliment
    0.25
     sexes
    0.25
    æĶ¯åĩº
    0.24
    ä¸Ńå¼ı
    0.24
     quarterback
    0.24
    Activations Density 4.858%

    No Known Activations