© 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. 6751
    Prev
    Next
    INDEX
    Explanations

    is not

    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
    åij¼åı«
    -0.09
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    çľĭä¸įè§ģ
    -0.08
    jian
    -0.08
    èµ°åĪ°
    -0.08
    æµ´
    -0.08
    ãģĭãģ©ãģĨãģĭ
    -0.08
    iers
    -0.08
    ias
    -0.07
    ç´§å¯Ĩç»ĵåIJĪ
    -0.07
    POSITIVE LOGITS
    SHARE
    0.10
    InSection
    0.09
    ä¸įè¡Į
    0.09
    çĤ®
    0.09
    ä½łä¼ļ
    0.09
    antha
    0.09
     riot
    0.08
     iÅŁlemleri
    0.08
    è¡Į人
    0.08
     Riot
    0.08
    Activations Density 0.024%

    No Known Activations