© 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. 53679
    Prev
    Next
    INDEX
    Explanations

    such [adjective/noun] as

    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
    åĽĽç§į
    -0.10
    çĺ¾
    -0.09
    ä¸īç§į
    -0.09
    两ç§į
    -0.09
    åıĺåİĭ
    -0.09
    çļĦæĸ¹å¼ıæĿ¥
    -0.09
    éĶ£
    -0.08
    DTV
    -0.08
    è¿Ļ两ç§į
    -0.08
    çŁ¥æĥħ
    -0.08
    POSITIVE LOGITS
    诸å¦Ĥ
    0.24
    å¦Ĥ
    0.17
    æ¯Ķå¦Ĥ
    0.16
    ä¾ĭå¦Ĥ
    0.15
     like
    0.15
     nhÆ°
    0.14
     wie
    0.12
     such
    0.12
    åĥı
    0.12
    æ¯Ķå¦Ĥ说
    0.12
    Activations Density 0.205%

    No Known Activations