© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32730
    Prev
    Next
    INDEX
    Explanations

    new titles or descriptions

    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
    æŃī
    -0.09
    ç»Ļ
    -0.09
    aniu
    -0.09
     Buckingham
    -0.08
    åĮĸçŁ³
    -0.08
    æİĮæı¡
    -0.08
    纯粹
    -0.08
     برÙĨ
    -0.08
    .absolute
    -0.08
    æĿŁ
    -0.08
    POSITIVE LOGITS
    è¦Ĩ
    0.09
    å¿ĥèĦıçĹħ
    0.09
     pads
    0.09
    工夫
    0.09
     treatment
    0.09
     Pad
    0.09
     fac
    0.08
    ç«Ń
    0.08
    åįĩ级æĶ¹éĢł
    0.08
    åį¡éĢļ
    0.08
    Activations Density 0.071%

    No Known Activations