© 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. 7346
    Prev
    Next
    INDEX
    Explanations

    university, fund, abeka, ville, atcher

    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
    à¸į
    -0.09
    è¾ŀ
    -0.08
    çļĩåIJİ
    -0.08
    åĪĩåī²
    -0.08
    转载
    -0.08
    åħ¼å®¹
    -0.08
    ç¾İ人
    -0.08
     Ñģобой
    -0.08
    è´·
    -0.08
    iated
    -0.08
    POSITIVE LOGITS
    èİ·
    0.09
    åŁºçĿ£æķĻ
    0.09
    cka
    0.09
     christian
    0.09
    .CG
    0.08
    è¿Ļ项
    0.08
    è¿Ļ件äºĭæĥħ
    0.08
    bout
    0.08
    çĸ¤
    0.08
    éĤ£æ®µ
    0.08
    Activations Density 0.140%

    No Known Activations