© 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. 26434
    Prev
    Next
    INDEX
    Explanations

    prove to be

    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
     اÙĦÙħÙĦ
    -0.09
    æī¯
    -0.09
    æ°´ä¸Ĭ
    -0.09
    åıijçİ°èĩªå·±
    -0.09
    çĽ¸å¯¹è¾ĥ
    -0.09
    å®ŀéĻħæĥħåĨµ
    -0.09
    ç³Łç³ķ
    -0.09
    è¾¹éĻħ
    -0.09
    æıĨ
    -0.09
    ãģĽãģĦ
    -0.09
    POSITIVE LOGITS
    ãģĦãģıãĤī
    0.09
    åīĮ
    0.09
    edores
    0.08
    annis
    0.08
    è¹ĭ
    0.08
    mes
    0.08
    RAP
    0.08
    æĹłç©·
    0.08
     Temper
    0.08
    ance
    0.08
    Activations Density 0.008%

    No Known Activations