© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9903
    Prev
    Next
    INDEX
    Explanations

    wi-fi

    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
     Ñģобой
    -0.10
    ries
    -0.09
    bos
    -0.08
     اÙĦÙħتÙĪسط
    -0.08
    æłĢ
    -0.08
    èĬ±æľµ
    -0.08
    æ´¼
    -0.08
     bosses
    -0.08
     redesign
    -0.07
    ouv
    -0.07
    POSITIVE LOGITS
    owski
    0.09
    ê»ı
    0.09
    è¿ĩæĿ¥
    0.09
    ingly
    0.09
    æµģåŁŁ
    0.09
    Ñħо
    0.09
    htub
    0.09
    ness
    0.09
     дело
    0.08
    娱
    0.08
    Activations Density 0.020%

    No Known Activations