© 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. 32073
    Prev
    Next
    INDEX
    Explanations

    places, events, or actions occurring

    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
     влад
    -0.10
    åħħå½ĵ
    -0.09
    æĪIJ为ä¸ŃåĽ½
    -0.09
    å¥ģ
    -0.09
    åĮ¡
    -0.08
    flux
    -0.08
    ETA
    -0.08
    åIJĦåľ°
    -0.08
    ugu
    -0.08
    ivot
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.14
    åıijçĶŁåľ¨
    0.13
    å°±åľ¨
    0.12
     ìĿ´ë£¨ìĸ´
    0.12
    åı¯åľ¨
    0.11
    åľ°çĤ¹
    0.11
    éĥ½åľ¨
    0.10
    åºĶåľ¨
    0.10
    åľ¨åĵªéĩĮ
    0.10
    åı¯ä»¥åľ¨
    0.10
    Activations Density 0.295%

    No Known Activations