© 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. 1015
    Prev
    Next
    INDEX
    Explanations

    able endings

    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
    è´¯
    -0.10
    èĥ½å¤Ł
    -0.10
    ãģĦãģ¾
    -0.10
    и
    -0.09
    æĹ¢åı¯ä»¥
    -0.09
    dv
    -0.09
    urf
    -0.08
    icom
    -0.08
    äºĨèĩªå·±çļĦ
    -0.08
    à¸ļา
    -0.08
    POSITIVE LOGITS
    keit
    0.11
    èĩªå¦Ĥ
    0.11
    é¢Ħè§ģ
    0.10
    æĺ¯ä¸Ģéĥ¨
    0.10
    æ¡´
    0.10
    貨
    0.09
    çŧ
    0.09
    æĢ§å¼º
    0.09
    .oc
    0.09
    æĮ¯åħ´
    0.09
    Activations Density 0.129%

    No Known Activations