© 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. 107282
    Prev
    Next
    INDEX
    Explanations

    it

    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
    aphrag
    -0.28
    oph
    -0.28
    åĬ¨ä½ľ
    -0.27
    itz
    -0.27
    _phr
    -0.27
    ç²Ł
    -0.26
    é«ĺæīĭ
    -0.25
    åıįèĢĮ
    -0.25
    _past
    -0.25
    çļĦåĬ¨ä½ľ
    -0.25
    POSITIVE LOGITS
    catalog
    0.31
     catalog
    0.25
     каÑĤалог
    0.25
    E
    0.24
    Catalog
    0.24
    éĢļ讯
    0.23
     Elev
    0.23
     catalogue
    0.23
    assed
    0.23
     Catalog
    0.23
    Activations Density 33.975%

    No Known Activations