© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35867
    Prev
    Next
    INDEX
    Explanations

    apply for

    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
     Ñģобой
    -0.11
    INGTON
    -0.09
    ì½ĺ
    -0.09
    éģĹæĨ¾
    -0.09
    æıIJä¾ĽåķĨ
    -0.09
    ilate
    -0.09
    æıIJä¾Ľä¼ĺè´¨
    -0.09
    CADE
    -0.09
    -flex
    -0.09
    illet
    -0.09
    POSITIVE LOGITS
    并éĢļè¿ĩ
    0.11
    沤
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    ä½łåĸľæ¬¢
    0.09
    åĬ©
    0.08
    äºĨä¸Ģç³»åĪĹ
    0.08
    æĪIJ为ä¸ŃåĽ½
    0.08
    amp
    0.08
    ä¸ĭéĿ¢æĪij们
    0.08
    æĹĦ
    0.08
    Activations Density 0.020%

    No Known Activations