© 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. 48491
    Prev
    Next
    INDEX
    Explanations

    best, worst, expect, unknown

    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
    eah
    -0.10
    omed
    -0.10
    eva
    -0.09
    æĴij
    -0.09
    说å¾Ĺ
    -0.09
    irectory
    -0.09
    олÑĮз
    -0.09
    MAS
    -0.08
    akk
    -0.08
    æĬĢ
    -0.08
    POSITIVE LOGITS
    åıĺæĢģ
    0.10
    asel
    0.10
    æĤ²è§Ĥ
    0.10
    è¾Ķ
    0.10
    åIJİæŀľ
    0.09
    åIJ¦å®ļ
    0.09
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.08
    ç«ĭéĿ¢
    0.08
    åį´åıĪ
    0.08
    ç¾İ好çļĦ
    0.08
    Activations Density 0.025%

    No Known Activations