© 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. 62776
    Prev
    Next
    INDEX
    Explanations

    progression

    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
    sans
    -0.26
     augmentation
    -0.25
    å°±èĥ½
    -0.24
    IDs
    -0.24
     lettre
    -0.24
    IOUS
    -0.24
     bour
    -0.24
    uctions
    -0.24
    她说
    -0.24
    spl
    -0.24
    POSITIVE LOGITS
    \uc
    0.28
    串
    0.27
    hind
    0.26
    æĥ¯ä¾ĭ
    0.26
     chim
    0.26
    /umd
    0.25
    oya
    0.25
    ذا
    0.24
    oy
    0.24
    享
    0.24
    Activations Density 9.648%

    No Known Activations