© 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. 24-TRANSCODER-HP
    7. 151106
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bounty
    -0.27
    gone
    -0.26
    港澳
    -0.26
     Bands
    -0.26
    ester
    -0.25
    åŁİ乡
    -0.24
     cli
    -0.24
     Ble
    -0.24
    cli
    -0.24
    -widget
    -0.23
    POSITIVE LOGITS
     ÑģÑĤÑĢ
    0.26
    æĦıåĽ¾
    0.26
    .Interval
    0.25
    第ä¸Ģç«ł
    0.25
     Hall
    0.24
    éļı
    0.24
    ENSOR
    0.24
    æĸ°äº§åĵģ
    0.24
    rig
    0.24
    ahn
    0.23
    Activations Density 1.116%

    No Known Activations