© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9288
    Prev
    Next
    INDEX
    Explanations

    colon followed by how

    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
    åİ¥
    -0.10
    æİ¡åıĸ
    -0.08
    顾èĻij
    -0.08
    ç£Ĭ
    -0.08
    éĩĩåıĸ
    -0.08
    幸
    -0.08
    avy
    -0.08
    åĽŀåºĶ
    -0.08
    enheim
    -0.08
    lyph
    -0.08
    POSITIVE LOGITS
    å®ģæĦ¿
    0.14
    寧
    0.13
    å®ģ
    0.13
    æĪijåĸľæ¬¢
    0.12
    æĪijè¿ĺæĺ¯
    0.11
    èĩªåľ¨
    0.11
    çļĦ人æĿ¥è¯´
    0.11
    âĺ°
    0.10
    å®Ī
    0.10
    ankan
    0.10
    Activations Density 0.168%

    No Known Activations