© 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. 27658
    Prev
    Next
    INDEX
    Explanations

    mathematical questions about derivatives and digits

    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
     Dip
    -0.09
    é¹³
    -0.08
     Hunting
    -0.08
     ÐłÐ°
    -0.08
    楼
    -0.08
    imar
    -0.08
    äºĭåħĪ
    -0.08
    鸱
    -0.07
    æĽ´æľī
    -0.07
    é¢ĦåħĪ
    -0.07
    POSITIVE LOGITS
    åħ®
    0.08
    æ¼Ķ
    0.08
    oyal
    0.08
    éĥ¡
    0.08
    麽
    0.08
    æŃ¤äºº
    0.08
    ettel
    0.08
    æºģ
    0.08
    被æīĵ
    0.08
    utow
    0.08
    Activations Density 0.087%

    No Known Activations