© 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. 64285
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    ä½ľåĵģåĨħ容
    -0.30
    ศาส
    -0.28
    汩
    -0.27
     distância
    -0.26
    ä¸įæĪIJ
    -0.26
    PyObject
    -0.25
    ritz
    -0.25
    -multi
    -0.25
    èĮĤ
    -0.25
     Tuesday
    -0.25
    POSITIVE LOGITS
    æºľ
    0.28
    èĢħçļĦ
    0.27
    ç»Ļ
    0.27
     aff
    0.26
    ãģ«è¡Į
    0.26
    èĢħãģ®
    0.25
    vn
    0.25
    èĢħ
    0.24
    Aff
    0.24
     Aff
    0.24
    Activations Density 7.467%

    No Known Activations