© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60694
    Prev
    Next
    INDEX
    Explanations

    LINBIT, Linotype, Linux, Linnaeus, LINQ, linaro, lincoln

    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
    Negative Logits
    åĴĮåľ°åĮº
    -0.12
    sWith
    -0.10
    eenth
    -0.10
    ein
    -0.10
    说æĺ¯
    -0.09
    ingly
    -0.09
    eur
    -0.09
    alach
    -0.09
    ä¸įåıĬ
    -0.09
    ãģĮãĤī
    -0.09
    POSITIVE LOGITS
    bourne
    0.09
    rad
    0.09
    ç¥Ĺ
    0.09
    æľīç§į
    0.08
     Lun
    0.08
    htm
    0.08
    æīĵæĬĺ
    0.08
     деÑıÑĤелÑĮноÑģÑĤÑĮ
    0.08
    fos
    0.08
    itial
    0.08
    Activations Density 0.011%

    No Known Activations