© 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. 23153
    Prev
    Next
    INDEX
    Explanations

    year completion

    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
    /or
    -0.10
    çļĦ人æĿ¥è¯´
    -0.08
    /etc
    -0.08
    à¹Ĥà¸ģ
    -0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.08
    ä¼Ĺ
    -0.08
    æĢĢéĩĮ
    -0.08
    å½±åĵįåĬĽçļĦ
    -0.07
    æīĭä¸Ń
    -0.07
    èĢĮæĺ¯
    -0.07
    POSITIVE LOGITS
    山寨
    0.10
    稽
    0.10
    åĬłä»¥
    0.10
    äºĨèµ·æĿ¥
    0.10
     اÙĦثاÙĦ
    0.09
    abilia
    0.09
    FindObject
    0.09
     دÙħØ´
    0.09
    åľ°åĮº
    0.09
    acias
    0.09
    Activations Density 0.626%

    No Known Activations