© 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. 9913
    Prev
    Next
    INDEX
    Explanations

    the rest

    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
    otherwise
    -0.10
    å¯Į
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    วล
    -0.09
    éªħ
    -0.09
     otherwise
    -0.08
     algun
    -0.08
    ä¸įçŁ¥éģĵ
    -0.08
    гÑĥ
    -0.08
    ä¸Ģ人
    -0.08
    POSITIVE LOGITS
    çļĦæŶéĹ´éĩĮ
    0.11
    cial
    0.10
    iale
    0.10
    CTOR
    0.10
    bei
    0.09
    æŶåĢĻ
    0.09
    ervers
    0.09
    adia
    0.09
    çļĦçĶŁæ´»
    0.09
    åİŁåĪĻä¸Ĭ
    0.09
    Activations Density 0.020%

    No Known Activations