© 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. 9782
    Prev
    Next
    INDEX
    Explanations

    from preschool, church camp, Facebook account

    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
    èĢģ乡
    -0.11
    bidden
    -0.10
    oop
    -0.09
    éħ¬
    -0.09
    anka
    -0.09
    åºķèķ´
    -0.09
    èĥ½è®©
    -0.09
    åİĨ代
    -0.09
    éĢĴç»Ļ
    -0.08
    arters
    -0.08
    POSITIVE LOGITS
    åģ¥åº·æĪIJéķ¿
    0.13
    ä»ĸèĩªå·±
    0.13
    æ¯ĶæĪij
    0.12
    è·ŁæĪij
    0.11
    帮æĪij
    0.11
    åŃ¦ä¹łæĪIJ绩
    0.11
    è·ŁæĪij说
    0.11
    å¤Ń
    0.11
    çĪ°
    0.10
     himself
    0.10
    Activations Density 0.125%

    No Known Activations