© 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. 59124
    Prev
    Next
    INDEX
    Explanations

    adoption or uptake

    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
    åħ¥åħļ
    -0.08
    æĬĢ
    -0.08
    aha
    -0.08
    idal
    -0.08
    åĩºèº«
    -0.08
    åĢ¼å¾Ĺä¸ĢæıIJ
    -0.08
    è¯Ĵ
    -0.08
    zet
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    æĢ«
    -0.08
    POSITIVE LOGITS
    çİĩ为
    0.12
    çİĩè¾¾åĪ°
    0.10
    颦
    0.10
    é¹ĥ
    0.10
    ë¥ł
    0.10
    æĸ°æĬĢæľ¯
    0.09
    çİĩè¾¾
    0.09
    çİĩ
    0.09
    ä¹ĭå¿ĥ
    0.09
    çļĦå¿ĥæĥħ
    0.09
    Activations Density 0.021%

    No Known Activations