© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63812
    Prev
    Next
    INDEX
    Explanations

    latest / newest followed by a noun

    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
    çķĽ
    -0.09
    çļĦåľ°æĸ¹
    -0.09
    è¿Ļ件äºĭ
    -0.09
    elong
    -0.09
    å°´å°¬
    -0.08
    å½ĵåīįä½įç½®
    -0.08
    ooth
    -0.08
    ลà¸ļ
    -0.08
    å¼ĢçĿĢ
    -0.08
    家çĶµ
    -0.08
    POSITIVE LOGITS
    çļĦæ°Ķæģ¯
    0.10
    -generation
    0.10
    ä¸Ģæ³¢
    0.10
    -focus
    0.09
    remium
    0.09
    缮åħī
    0.09
    æݨåĩºçļĦ
    0.09
    æįĤ
    0.09
    izzle
    0.09
    heits
    0.09
    Activations Density 0.037%

    No Known Activations