© 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. 149314
    Prev
    Next
    INDEX
    Explanations

    gibberish

    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
    Negative Logits
    most
    -0.27
    lish
    -0.26
    :\/\/
    -0.25
    erland
    -0.24
    æĥº
    -0.24
    æ·»
    -0.24
    burgh
    -0.23
     breadcrumbs
    -0.23
    åıijå¸ĥæŶéĹ´
    -0.23
    æĺ¯æĪijåĽ½
    -0.23
    POSITIVE LOGITS
    rem
    0.25
    å°ĸåı«
    0.24
     Heights
    0.24
    iscal
    0.24
    ovie
    0.24
     columnName
    0.24
    ä¸ªå·¥ä½ľ
    0.23
     Rem
    0.23
    éis
    0.23
     CÆ¡
    0.23
    Activations Density 0.147%

    No Known Activations