© 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. 31671
    Prev
    Next
    INDEX
    Explanations

    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
    éĤ£ä¹Īå¤ļ
    -0.11
    æ¯Ķè¾ĥå¤ļ
    -0.10
    nten
    -0.10
    оÑĦ
    -0.10
     gì
    -0.10
     иÑģÑĤоÑĢиÑı
    -0.10
    ãģ°ãģĭãĤĬ
    -0.10
    éĿŀ常å¤ļ
    -0.10
    تد
    -0.10
     оÑĤзÑĭв
    -0.09
    POSITIVE LOGITS
    æŃ£å¸¸çļĦ
    0.09
    å¹³éĿĻ
    0.08
     its
    0.08
     dec
    0.08
    ear
    0.08
    çĪ¶åŃIJ
    0.08
    fo
    0.08
    æĺĢ
    0.08
    pic
    0.08
    umer
    0.07
    Activations Density 0.023%

    No Known Activations