© 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. 17707
    Prev
    Next
    INDEX
    Explanations

    from [location/possessive]

    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
    å©´
    -0.10
    å¨ĥå¨ĥ
    -0.09
    å°ıåŃ©åŃIJ
    -0.09
    è¹Ń
    -0.09
    æķijæµİ
    -0.09
    æŁIJç§į
    -0.09
    æĺ¼
    -0.09
    åŁºéĩijä¼ļ
    -0.09
    oc
    -0.09
    pike
    -0.08
    POSITIVE LOGITS
    è§ĴèIJ½
    0.10
    ISE
    0.09
    æİĬ
    0.08
    çı¾åł´
    0.08
    å¢Ĵ
    0.08
    çİ°åľº
    0.08
    å¸ļ
    0.08
    ноÑģ
    0.08
    åĹ
    0.08
    stras
    0.08
    Activations Density 0.054%

    No Known Activations