© 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. 34670
    Prev
    Next
    INDEX
    Explanations

    apply applicable law

    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
     TOK
    -0.10
    ä¸įèĩ³äºİ
    -0.09
    æİĢèµ·
    -0.08
    èĥ½å¤Łè®©
    -0.08
    æĴij
    -0.08
    ä»Ĩ
    -0.08
    æīĺ
    -0.08
    æĻ¯å¾·
    -0.08
    emon
    -0.08
    翼
    -0.08
    POSITIVE LOGITS
    éĢĤçĶ¨äºİ
    0.23
    éĢĤçĶ¨
    0.22
     applies
    0.22
    éģ©çĶ¨
    0.19
     apply
    0.19
     Applies
    0.19
     applicable
    0.19
     ìłģìļ©
    0.16
    apply
    0.16
    _apply
    0.16
    Activations Density 0.075%

    No Known Activations