© 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. 49915
    Prev
    Next
    INDEX
    Explanations

    names, titles, and people

    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
     trữ
    -0.10
    è½
    -0.09
    หาย
    -0.09
     sobie
    -0.09
    ILED
    -0.09
    aret
    -0.09
    糯
    -0.09
    ibr
    -0.09
    _handlers
    -0.09
    çĪ·
    -0.09
    POSITIVE LOGITS
    é¢ĸ
    0.09
    æ¾ľ
    0.08
    寤
    0.08
    çļĦæĪIJéķ¿
    0.08
    acle
    0.08
    èĤ²
    0.08
     tight
    0.08
    çĮ¿
    0.08
    çļĦ年轻人
    0.08
     favored
    0.07
    Activations Density 0.106%

    No Known Activations