© 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. 10108
    Prev
    Next
    INDEX
    Explanations

    cities and sporting events

    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
    åľ¨æ¸¸æĪıä¸Ń
    -0.11
    åľ¨åŃ¦æł¡
    -0.10
    åľ¨åľ°ä¸Ĭ
    -0.10
    åľ¨å¤ĸéĿ¢
    -0.10
    æ´»è·ĥ
    -0.09
    åŃĺåľ¨äºİ
    -0.09
     Ñĥзн
    -0.09
    ìĮį
    -0.09
    æĬ¤çħ§
    -0.09
     Volt
    -0.09
    POSITIVE LOGITS
     же
    0.08
     Springs
    0.08
    ä¸Ģçīĩ
    0.08
    éĤ£
    0.08
    orca
    0.08
    xes
    0.08
    åķ¼
    0.08
    -based
    0.08
    -area
    0.08
    avras
    0.08
    Activations Density 0.030%

    No Known Activations