© 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. 22800
    Prev
    Next
    INDEX
    Explanations

    happens to be

    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
    ä¸įå°½
    -0.10
    acl
    -0.09
    otto
    -0.09
    ç®Ģ缴
    -0.09
    ç®Ģ缴æĺ¯
    -0.09
     Ivory
    -0.08
    åı¯è°ĵæĺ¯
    -0.08
    енÑĮ
    -0.08
    åĵ¡
    -0.08
    ä¸įä¹ħ
    -0.08
    POSITIVE LOGITS
     Moment
    0.10
    ubb
    0.10
    æĺ¯æĪijåĽ½
    0.09
    ties
    0.09
    nd
    0.09
    amber
    0.08
    ä¹Łæ¯Ķè¾ĥ
    0.08
    æĺ¯çĶ¨æĿ¥
    0.08
    ä¹ŁéĿŀ常
    0.08
    æĺ¯è°ģ
    0.08
    Activations Density 0.007%

    No Known Activations