© 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. 27809
    Prev
    Next
    INDEX
    Explanations

    privacy policies and data security

    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
    èĢĨ
    -0.11
    ä¸įåı¯æĢĿè®®
    -0.10
    åĭī
    -0.09
     cabinets
    -0.09
    æĹ©æĹ¥
    -0.09
    æľ«ç«¯
    -0.09
    xDF
    -0.09
    inee
    -0.09
    æĤ£çĹħ
    -0.09
    æĹ©
    -0.09
    POSITIVE LOGITS
    éļIJç§ģ
    0.10
     privacy
    0.10
    é¹ŀ
    0.09
    мол
    0.09
     ven
    0.08
    éĢıæ°Ķ
    0.08
     Privacy
    0.08
     Damon
    0.08
    privacy
    0.08
    Privacy
    0.08
    Activations Density 0.094%

    No Known Activations