© 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. 18223
    Prev
    Next
    INDEX
    Explanations

    it all began/started

    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
    éĩįæķ´
    -0.09
    .fc
    -0.08
    æĶ¿æ³ķ
    -0.08
    éĥľ
    -0.08
    çĸıéĢļ
    -0.08
    èĨĿ
    -0.08
    ä½Ĺ
    -0.08
    æļĤ
    -0.08
     Dude
    -0.08
    禳
    -0.07
    POSITIVE LOGITS
    å§ĭäºİ
    0.21
    èµ·æºIJ
    0.20
    èµ·çĤ¹
    0.17
     наÑĩал
    0.17
    èµ·æŃ¥
    0.17
    æºIJ头
    0.15
     ìĭľìŀij
    0.15
    å¼Ģå§ĭ
    0.15
    å¼Ģ端
    0.15
    å§ĭ
    0.14
    Activations Density 0.081%

    No Known Activations