© 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. 38483
    Prev
    Next
    INDEX
    Explanations

    integral part of

    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
    æĪijèĩªå·±
    -0.10
    ä½łèĩªå·±
    -0.09
    ÙĪتر
    -0.09
    æīĵåĩ»
    -0.09
    çªľ
    -0.09
     sing
    -0.08
     fort
    -0.08
     Minds
    -0.08
    å¾Īéķ¿
    -0.08
    æĪijåİ»
    -0.08
    POSITIVE LOGITS
     part
    0.23
    çļĦä¸Ģéĥ¨åĪĨ
    0.22
     ÑĩаÑģÑĤÑĮ
    0.20
    ä¸Ģéĥ¨åĪĨ
    0.19
    ç»ĦæĪIJéĥ¨åĪĨ
    0.16
     parte
    0.16
    èŀįåħ¥
    0.14
     parts
    0.14
    ä¸Ģä½ĵ
    0.14
     ÑĩаÑģÑĤи
    0.13
    Activations Density 0.137%

    No Known Activations