© 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. 20-TRANSCODER-HP
    7. 62668
    Prev
    Next
    INDEX
    Explanations

    process/method stages or components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    /MIT
    -0.27
    以ä¸ĭæĺ¯
    -0.26
    idel
    -0.26
    ç§ģæľį
    -0.25
     baÅŁÄ±na
    -0.25
     unspecified
    -0.25
     Pods
    -0.25
    exual
    -0.25
    è¾ĥ
    -0.25
    pery
    -0.24
    POSITIVE LOGITS
    ä¸ĢæŃ¥æŃ¥
    0.28
    éĢIJ
    0.26
    æĭ¿æĿ¥
    0.25
    æ²½
    0.25
    TEST
    0.24
    åı¯çĶ¨äºİ
    0.24
    _tests
    0.24
    æݨå¼Ģ
    0.24
    对åѦçĶŁ
    0.24
    æŀĦæĪIJäºĨ
    0.24
    Activations Density 8.464%

    No Known Activations