© 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. 21605
    Prev
    Next
    INDEX
    Explanations

    due to

    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
    æľīæĿ¡ä»¶çļĦ
    -0.10
    æľīä¿¡å¿ĥ
    -0.09
    鸷
    -0.09
    ä¸Ģçľĭ
    -0.09
    oret
    -0.09
    ä¹Łå°±æĺ¯è¯´
    -0.09
    éļħ
    -0.09
    ä¿Ł
    -0.09
     Kore
    -0.09
    çļĦåģļæ³ķ
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.15
    ç§įç§į
    0.13
    åħ¶
    0.11
    çĸ«æĥħå½±åĵį
    0.09
    å½±åĵįåĬĽçļĦ
    0.09
     its
    0.09
    æŁIJç§į
    0.09
    æĪijèĩªå·±
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
     being
    0.08
    Activations Density 0.074%

    No Known Activations