© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26734
    Prev
    Next
    INDEX
    Explanations

    positive evaluation or description

    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
    éĿŀ常好çļĦ
    -0.10
    éĥ½æĺ¯éĿŀ常
    -0.10
    éĿŀ常好
    -0.09
    åįķèģĮä¸ļ
    -0.09
    没æľīæĥ³åĪ°
    -0.09
    éĿŀ常çļĦ
    -0.09
    æħ¢æħ¢çļĦ
    -0.09
    riot
    -0.09
    ä¹Łæĺ¯å¾Ī
    -0.09
    ersen
    -0.09
    POSITIVE LOGITS
    åĵªæĢķ
    0.09
    è¿ĻèĪ¬
    0.09
    åĢĺèĭ¥
    0.09
    åį³ä¾¿
    0.08
    èĢĮéĿŀ
    0.08
    äºĭåĦ¿
    0.08
    ãģłãģ£ãģ¦
    0.08
    çĿ¥
    0.08
    æĦĪåıij
    0.07
    çŃļ
    0.07
    Activations Density 1.652%

    No Known Activations