© 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. 53774
    Prev
    Next
    INDEX
    Explanations

    expertise and strengths

    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
    æľĿçĿĢ
    -0.10
    éŃ
    -0.09
    ìĤ¬ë¥¼
    -0.09
    åİŁåĽłæĺ¯
    -0.08
    åħ¬ç¤¾
    -0.08
    æľŁéĸĵ
    -0.08
    æł·
    -0.08
    MENTS
    -0.08
    æĶ¿çŃĸæݪæĸ½
    -0.08
    /details
    -0.08
    POSITIVE LOGITS
    æĵħéķ¿
    0.21
    çī¹éķ¿
    0.14
     expertise
    0.14
    à¸ĸà¸Ļ
    0.13
    é¢ĨåŁŁ
    0.11
    çĨŁæĤīçļĦ
    0.11
    å¾ĹæĦı
    0.11
     strengths
    0.11
    æĵħ
    0.10
    ä¸ĢåIJij
    0.10
    Activations Density 0.063%

    No Known Activations