© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107551
    Prev
    Next
    INDEX
    Explanations

    like

    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
    è¾ĸ
    -0.31
    isers
    -0.28
    -neck
    -0.27
    encies
    -0.26
    æĿ¥èĩª
    -0.25
    ä»ij
    -0.25
    converter
    -0.24
     crest
    -0.24
    顾
    -0.24
     tast
    -0.24
    POSITIVE LOGITS
    åIJĪçIJĨçļĦ
    0.28
     busy
    0.27
    ofilm
    0.26
    广åijĬæľįåĬ¡
    0.25
    åIJĥä»Ģä¹Ī
    0.24
    æĹłç¼ĺ
    0.24
    deo
    0.24
    dao
    0.24
     Ih
    0.24
     reasonable
    0.24
    Activations Density 11.266%

    No Known Activations