© 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. 21781
    Prev
    Next
    INDEX
    Explanations

    indicates location

    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
    ä¸ŃåĽ½ä¼łç»Ł
    -0.09
    /c
    -0.08
    2
    -0.08
    3
    -0.08
    4
    -0.08
    5
    -0.08
    åľ¨è¿ĻéĩĮ
    -0.08
    åIJİéĿ¢
    -0.07
    8
    -0.07
    ãģı
    -0.07
    POSITIVE LOGITS
    abouts
    0.11
    anes
    0.10
    getManager
    0.10
    -même
    0.10
    èĢģ人家
    0.09
    çĮ±
    0.09
    ç»Ī身
    0.09
    å¼Ĥåij³
    0.09
    tones
    0.09
    è¿Ļä¸ªåľ°æĸ¹
    0.09
    Activations Density 0.025%

    No Known Activations