© 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. 30115
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers or star

    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
    å¿«æĬ¥
    -0.10
     Intl
    -0.09
    éĻ¶
    -0.09
     Luz
    -0.09
    å¾ģ
    -0.08
    ãģ¾ãģļ
    -0.08
    aho
    -0.08
    éľģ
    -0.08
     levy
    -0.08
    大åıij
    -0.08
    POSITIVE LOGITS
    éĤ£ä¹Īç®Ģåįķ
    0.11
     przecież
    0.10
    èĢģ人家
    0.10
    éĤ£ä¹Ī容æĺĵ
    0.10
    æ¯ıä¸Ģ天
    0.09
    rne
    0.08
    éĤ£æł·çļĦ
    0.08
     полно
    0.08
    çĥŃè¡Ģ
    0.08
    éĤ£éº¼
    0.08
    Activations Density 0.078%

    No Known Activations