© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17371
    Prev
    Next
    INDEX
    Explanations

    code snippets and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    most
    -0.09
    elves
    -0.09
    ities
    -0.08
    .builders
    -0.08
    å¤§èµĽ
    -0.08
    è®®æ¡Ī
    -0.08
    ials
    -0.08
    å¿ĥ缮ä¸Ń
    -0.08
    .eye
    -0.08
    еÑģ
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.11
    WithName
    0.09
    light
    0.09
    edException
    0.09
    edly
    0.08
    éķĹ
    0.08
    eds
    0.08
    ÑĤол
    0.08
    án
    0.08
    ãģ¡ãģª
    0.08
    Activations Density 0.002%

    No Known Activations