© 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. 107655
    Prev
    Next
    INDEX
    Explanations

    )

    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
    .wh
    -0.26
    é½Ĭ
    -0.25
    é½IJ
    -0.24
    å¾ĹåĪĨ
    -0.24
     riot
    -0.24
    åĭģ
    -0.24
    妥
    -0.24
    PY
    -0.23
    æį
    -0.23
    SSFWorkbook
    -0.23
    POSITIVE LOGITS
    oleans
    0.26
     IonicModule
    0.26
    rique
    0.24
    ounder
    0.24
     Boolean
    0.24
     Böl
    0.24
    æıIJåĩº
    0.24
    extent
    0.23
    åĢĴå¡Į
    0.23
    æĸĻ
    0.23
    Activations Density 9.754%

    No Known Activations