© 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. 55223
    Prev
    Next
    INDEX
    Explanations

    busy places and traffic

    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
    å·©
    -0.09
    çĻ½éĽª
    -0.09
     @[
    -0.09
    èĮģ
    -0.09
    éĶħ
    -0.09
    esa
    -0.08
    纡
    -0.08
    esz
    -0.08
    æĽ´ä½İ
    -0.08
    íıIJ
    -0.08
    POSITIVE LOGITS
     frequ
    0.14
    ç¹ģå¿Ļ
    0.13
    çĥŃéŨ
    0.12
    交éĢļæŀ¢çº½
    0.12
    é¢ijç¹ģ
    0.11
    交éĢļ
    0.11
    æŀ¢çº½
    0.11
    人æµģ
    0.11
    åľ°æ®µ
    0.10
    åĴ½åĸī
    0.10
    Activations Density 0.116%

    No Known Activations