© 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. 64877
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    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
    ScreenState
    -0.28
    :result
    -0.27
    jerne
    -0.27
    çŁ¿ä¸ļ
    -0.27
    #/
    -0.27
    è¾±
    -0.27
    erview
    -0.27
    letic
    -0.26
    æīĵåĩº
    -0.26
    ARDS
    -0.26
    POSITIVE LOGITS
    lek
    0.31
    çļĦçģµéŃĤ
    0.31
    opoulos
    0.27
    actions
    0.26
    objects
    0.26
    izations
    0.25
    without
    0.25
    éŀį
    0.25
     appar
    0.25
    n
    0.25
    Activations Density 2.344%

    No Known Activations