© 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. 31938
    Prev
    Next
    INDEX
    Explanations

    travel, DNA, participant, book, stock, registered, visited

    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
    togroup
    -0.10
    æ¯ĶåĪĨ
    -0.10
    PropertyParams
    -0.09
    ButtonTitles
    -0.09
    ä¸ĭæ²ī
    -0.09
    па
    -0.09
    оваÑĢ
    -0.08
    icht
    -0.08
    ValueHandling
    -0.08
    lotte
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.09
     presumably
    0.09
     некоÑĤоÑĢ
    0.09
     Nikki
    0.09
    ç¾
    0.08
    æĪijä»¬çŁ¥éģĵ
    0.08
     Highlander
    0.08
    advisor
    0.07
    çŃ¹
    0.07
    umm
    0.07
    Activations Density 1.147%

    No Known Activations