© 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. 129450
    Prev
    Next
    INDEX
    Explanations

    damage and repair

    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
    ionale
    -0.25
    éļ¾
    -0.24
    ually
    -0.24
    UnderTest
    -0.24
    çī¹æ®ĬæĥħåĨµ
    -0.24
    asts
    -0.24
    istics
    -0.23
    _prep
    -0.23
    Sept
    -0.23
    ativity
    -0.23
    POSITIVE LOGITS
    GRAM
    0.28
     Shuffle
    0.27
    нал
    0.25
    åģļäºĭ
    0.24
    å¿«éĢŁå¢ŀéķ¿
    0.24
    ä¸Ģåı£æ°Ķ
    0.24
    ãģ°ãģĭãĤĬ
    0.24
    ä¸Ģç«Ļ
    0.24
     Loaded
    0.24
    æĽ´æ·±
    0.23
    Activations Density 17.925%

    No Known Activations