© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6885
    Prev
    Next
    INDEX
    Explanations

    legal cases v. state

    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
    黥
    -0.09
    é«»
    -0.09
    ä¸ĸ人
    -0.09
    tered
    -0.09
     Hispan
    -0.09
    è´¢çī©
    -0.09
    æºĥ
    -0.09
    çĶļèĩ³è¿ĺ
    -0.08
     Kerr
    -0.08
    ç¢Ľ
    -0.08
    POSITIVE LOGITS
    主管éĥ¨éŨ
    0.09
    çłĮ
    0.09
    æ®Ĩ
    0.08
    çĿ«
    0.08
    gba
    0.08
     Markus
    0.08
    éĻĨç»Ń
    0.08
    arus
    0.08
    ائÙģ
    0.07
     Barg
    0.07
    Activations Density 0.099%

    No Known Activations