© 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. 27771
    Prev
    Next
    INDEX
    Explanations

    application of substances

    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°¾
    -0.09
    æĺ¯ä¸Ģ款
    -0.08
    çģŃ
    -0.08
     favourite
    -0.07
    èĤĨ
    -0.07
     favorite
    -0.07
    åħ³éĶ®åŃĹ
    -0.07
    4
    -0.07
    墨
    -0.07
    Cop
    -0.07
    POSITIVE LOGITS
    éķ«
    0.11
    以人为
    0.10
    åIJĦç±»
    0.10
    æ¶İ
    0.10
    æĺ¨å¤©
    0.10
    Ä±ÅŁ
    0.09
    æĹĦ
    0.09
    æīĵ交éģĵ
    0.09
    çĮľæµĭ
    0.09
    éĿ¢çĻ½
    0.09
    Activations Density 0.190%

    No Known Activations