© 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. 50159
    Prev
    Next
    INDEX
    Explanations

    Fried, ried, fried

    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
    stell
    -0.09
    æĤĴ
    -0.09
    lvl
    -0.08
    инг
    -0.08
    绸
    -0.08
    ä¸įéĹ´
    -0.08
    æĬ«éľ²
    -0.08
    å°ıé¢Ŀ贷款
    -0.08
    çIJĨäºĭä¼ļ
    -0.08
    ivor
    -0.08
    POSITIVE LOGITS
    ÑĦи
    0.09
    missible
    0.09
    ائÙĤ
    0.09
    miss
    0.09
    çļĦä¸ľè¥¿
    0.09
    ä¹
    0.09
    客æĪ·æıIJä¾Ľ
    0.09
    ocate
    0.08
    éĵĨ
    0.08
    дей
    0.08
    Activations Density 0.002%

    No Known Activations