© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12084
    Prev
    Next
    INDEX
    Explanations

    team success or performance

    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
    éŀħ
    -0.10
    èµĽåIJİ
    -0.09
    adm
    -0.09
    ä¹ħ
    -0.09
    åĪ¤å®ļ
    -0.09
    éĶ¦æłĩ
    -0.09
    åīįä¸Ģ天
    -0.08
    pag
    -0.08
    åĨ²åĬ¨
    -0.08
    æķ°æį®ä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
    çĶ¨äºº
    0.10
    ä¿¡å¿ĥ
    0.09
    éĩįç»Ħ
    0.09
    ä¸Ģå¹´
    0.09
    éĢĤåºĶ
    0.08
    ваÑĤ
    0.08
    æĶĺ
    0.08
    人åĿĩ
    0.08
    è¿Ļä¸Ģå¹´
    0.08
    åĽ¢å§Ķ
    0.08
    Activations Density 0.034%

    No Known Activations