© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    diet choices

    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
    èĬ±æľµ
    -0.11
    æĦŁåĬ¨
    -0.10
    éļ¾çĤ¹
    -0.10
    éĿ¢åŃIJ
    -0.09
    åħ±é¸£
    -0.09
    keh
    -0.09
    çĹĴ
    -0.09
    触åĬ¨
    -0.08
    пÑĥÑĤ
    -0.08
    doch
    -0.08
    POSITIVE LOGITS
    åĿĩè¡¡
    0.12
    æijĦåħ¥
    0.12
    é¥®é£Ł
    0.11
    æıIJåĢ¡
    0.11
    ä½ľæģ¯
    0.10
    æ¯ı天
    0.10
    çĶŁæ´»æĸ¹å¼ı
    0.10
    建议
    0.10
    åģ¥åº·
    0.10
    é¤IJ
    0.10
    Activations Density 0.108%

    No Known Activations