© 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. 57422
    Prev
    Next
    INDEX
    Explanations

    soul, heart, mind

    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
    åĬłåĢį
    -0.10
    å½ĴæĿ¥
    -0.09
    åıijæĮ¥
    -0.09
    uran
    -0.09
    æ°´æĻ¶
    -0.09
     ÑĢей
    -0.08
    åºĶçĶ¨äºİ
    -0.08
    çĪª
    -0.08
    æĬĵèİ·
    -0.08
    ij
    -0.08
    POSITIVE LOGITS
    åºķæ°Ķ
    0.10
     полно
    0.10
     Cel
    0.09
    ä¸įæŃ»
    0.09
    纪å¾ĭ
    0.09
    ÑĦе
    0.09
    ÑĪен
    0.09
    翼
    0.08
    è´¨éĩıåĴĮ
    0.08
    boarding
    0.08
    Activations Density 0.027%

    No Known Activations