© 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. 23225
    Prev
    Next
    INDEX
    Explanations

    find out

    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
    æīĵæŃ»
    -0.11
    åģ¥åº·æĪIJéķ¿
    -0.10
    éĤĪ
    -0.10
    åºIJ
    -0.10
    ä¸įæĪIJ
    -0.09
    æĶ¾æīĭ
    -0.09
    lâ
    -0.09
    ives
    -0.09
    oji
    -0.09
    åħįç¨İ
    -0.09
    POSITIVE LOGITS
    ubber
    0.09
    å¾ĹçŁ¥
    0.09
    ابر
    0.08
    ç»Ŀ
    0.08
     savoir
    0.08
    ä¹İ
    0.08
    ucci
    0.08
    Ops
    0.08
    Compat
    0.08
    仿
    0.08
    Activations Density 0.021%

    No Known Activations