© 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. 5117
    Prev
    Next
    INDEX
    Explanations

    of others, friends, class

    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
    讽
    -0.09
    æŀķ
    -0.09
    ê³Ħ
    -0.09
    æłİ
    -0.08
    éļIJ
    -0.08
    FIN
    -0.08
    indx
    -0.08
    çĭ¸
    -0.08
    errick
    -0.08
     Bennett
    -0.08
    POSITIVE LOGITS
    åIJĮè¡Į
    0.12
    ä¸ĢåIJĮ
    0.12
    åIJĮä¸ļ
    0.11
    ç«ŀäºī
    0.11
     fellow
    0.11
    çļĦç«ŀäºī
    0.11
    åIJĮç±»
    0.10
    競çĪŃ
    0.10
    åIJĮæľŁ
    0.10
    åħ¶ä»ĸ
    0.10
    Activations Density 0.082%

    No Known Activations