© 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. 48964
    Prev
    Next
    INDEX
    Explanations

    price, costs, discounts, savings, guaranteed

    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
    éĽī
    -0.11
    骥
    -0.09
    çĶ¨æīĭ
    -0.09
    tring
    -0.09
    reated
    -0.08
    _identity
    -0.08
    驼
    -0.08
    åı
    -0.08
    ÃŃd
    -0.08
    acted
    -0.08
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.13
    为æĤ¨
    0.12
    ä¸ºä½ł
    0.11
    çļĦç«ŀäºī
    0.10
    ç«ŀäºīåĬĽ
    0.10
    æĽ´ä½İ
    0.10
    ç»Ļä½ł
    0.10
    询
    0.10
    让æĤ¨
    0.10
     undercut
    0.09
    Activations Density 0.035%

    No Known Activations