© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20130
    Prev
    Next
    INDEX
    Explanations

    academic courses and classes

    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
    æķĻèĤ²èµĦæºIJ
    -0.09
     Nicola
    -0.09
    åŃIJå¼Ł
    -0.08
    æįĤ
    -0.08
    æĺ¯åľ¨
    -0.08
    åŁºç¡Ģ设æĸ½
    -0.08
    åħ®
    -0.08
    å¹¿æ³Ľ
    -0.08
    mere
    -0.08
     Storm
    -0.08
    POSITIVE LOGITS
    çIJĽ
    0.10
    失踪
    0.10
    åķĥ
    0.10
    åİŁçIJĨ
    0.09
    群
    0.09
    æ¦Ĥ
    0.09
    ä¼ļè§ģ
    0.09
    移åĬ¨
    0.09
    rious
    0.09
    hell
    0.09
    Activations Density 0.060%

    No Known Activations