© 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. 35277
    Prev
    Next
    INDEX
    Explanations

    offering services

    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
    éĢ¼
    -0.10
    è¿Ļæī¹
    -0.10
    å·¥å§Ķ
    -0.10
    è¿Ļå¥Ĺ
    -0.10
    testdata
    -0.10
    æĬĬæı¡
    -0.09
    izin
    -0.09
    èĸ¤
    -0.09
    éĻ¸
    -0.09
    æĬ¤èĤ¤åĵģ
    -0.09
    POSITIVE LOGITS
    æĺ¥ç§ĭ
    0.11
     services
    0.09
     ÑĥÑģлÑĥг
    0.09
    éľ°
    0.08
    代
    0.08
    éŀł
    0.08
    ä¸ĬéŨ
    0.08
    empor
    0.08
    æ¡ħ
    0.08
    çĦī
    0.08
    Activations Density 0.059%

    No Known Activations