© 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. 61730
    Prev
    Next
    INDEX
    Explanations

    systems and operation

    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
    è¿ĺæľª
    -0.09
    çĤ¹åįĬ
    -0.09
    çIJĨè´¢
    -0.09
     accom
    -0.08
    è°ĥåĬ¨
    -0.08
    erot
    -0.08
    蹬
    -0.08
    éĺ¶æ¢¯
    -0.08
    tight
    -0.08
    /react
    -0.08
    POSITIVE LOGITS
    çģ«èĬ±
    0.10
    edin
    0.10
    ç»ŀ
    0.09
    å¤ĸåĮħ
    0.09
    æ¦ĸ
    0.09
    ?key
    0.09
    enen
    0.09
    è´µ
    0.09
    -plugins
    0.09
    å¯ĦãģĽ
    0.09
    Activations Density 0.203%

    No Known Activations