© 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. 62620
    Prev
    Next
    INDEX
    Explanations

    time after

    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
    çłĶåĪ¤
    -0.10
    fur
    -0.09
    åľ°éģĵ
    -0.09
    èıĬ
    -0.09
    urs
    -0.09
    å¥¥åľ°
    -0.09
    éĢ¼
    -0.08
    ATS
    -0.08
    forcing
    -0.08
    æ·±è¿ľ
    -0.08
    POSITIVE LOGITS
     previously
    0.14
    以åīį
    0.14
    è¿ĩåİ»çļĦ
    0.13
     previous
    0.13
    èĩªä»İ
    0.13
    以å¾Ģ
    0.12
    å¤ļå¹´æĿ¥
    0.12
     ÑĢанее
    0.12
    å¤ļå¹´
    0.12
    æĽ¾ç»ı
    0.12
    Activations Density 0.152%

    No Known Activations