© 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. 33414
    Prev
    Next
    INDEX
    Explanations

    Kelly Services, Investment Management, Engineering Corporation

    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
    ermen
    -0.11
    åį·
    -0.09
    çľ·
    -0.09
    enson
    -0.09
     TERMS
    -0.09
    emean
    -0.09
    anco
    -0.09
    owell
    -0.08
    è´«
    -0.08
    æ±°
    -0.08
    POSITIVE LOGITS
    lite
    0.10
    ä¾į
    0.09
    ç·
    0.09
    æ¯Ľ
    0.09
    é«ĵ
    0.09
    æ²»å®ī
    0.09
    èħ´
    0.09
    åħ¬åı¸çļĦ
    0.08
    å¸ĤåĢ¼
    0.08
    _testing
    0.08
    Activations Density 0.063%

    No Known Activations