© 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. 27511
    Prev
    Next
    INDEX
    Explanations

    questions and greetings

    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
    æķ£
    -0.09
    èĦĨå¼±
    -0.09
    عاÙĨ
    -0.09
    æĹıèĩªæ²»
    -0.09
    otle
    -0.08
    çĬŁ
    -0.08
    ä¹ŀ
    -0.08
    æĭĻ
    -0.08
    çļĦæĦıæĢĿ
    -0.08
    人æĢ§åĮĸ
    -0.08
    POSITIVE LOGITS
    éĵł
    0.09
    å½ĵåĪĿ
    0.09
    åŁºæľ¬æĥħåĨµ
    0.09
    æĿı
    0.09
    é¦ĸåħĪ
    0.09
    è´µ
    0.08
    大åĬĽæİ¨è¿Ľ
    0.08
    é²Ł
    0.08
    å±ħ室
    0.08
    é¾Ħ
    0.08
    Activations Density 0.063%

    No Known Activations