© 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. 129365
    Prev
    Next
    INDEX
    Explanations

    ash

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Ñĩем
    -0.28
    jer
    -0.27
     ball
    -0.27
    奥æĸ¯
    -0.25
    baru
    -0.24
     UNION
    -0.24
    getic
    -0.24
    æĶ¯æŁ±
    -0.24
    uptools
    -0.23
    versible
    -0.23
    POSITIVE LOGITS
    ock
    0.28
    olin
    0.28
    ocking
    0.27
    anga
    0.25
     allo
    0.24
     Levin
    0.24
    rf
    0.23
    年产
    0.23
     Fallen
    0.23
    微信åħ¬ä¼Ĺ
    0.23
    Activations Density 1.783%

    No Known Activations