© 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. 34209
    Prev
    Next
    INDEX
    Explanations

    scandals, allegations, charges, troubles

    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
    åĮ£
    -0.10
     Blanch
    -0.09
    çļĦ第ä¸Ģ个
    -0.09
    è¾ĸ
    -0.09
    flush
    -0.09
    éķ¿æķĪ
    -0.09
    她说
    -0.08
    çŀİ
    -0.08
    arme
    -0.08
    ÑģÑĥ
    -0.08
    POSITIVE LOGITS
    åĵģå¾·
    0.12
    ä½ľé£İ
    0.11
    peg
    0.11
    éĨī
    0.10
    æ±ļ
    0.09
    æħĿ
    0.09
    åIJ¸æ¯Ĵ
    0.09
     scandals
    0.09
    æĮĤ
    0.09
    è¹Ī
    0.09
    Activations Density 0.121%

    No Known Activations