© 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. 49375
    Prev
    Next
    INDEX
    Explanations

    sensible, sense, sentimental, sane

    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
    pis
    -0.09
    strup
    -0.08
    ../../../
    -0.08
    çĽ²çĽ®
    -0.08
    pend
    -0.07
     Notre
    -0.07
    ffic
    -0.07
    ability
    -0.07
     Dalton
    -0.07
    лов
    -0.07
    POSITIVE LOGITS
    æ¨Ĺ
    0.12
    æĺ¯éŁ©åĽ½
    0.11
    ãģªãģı
    0.11
    MLS
    0.10
    车åŃIJ
    0.10
     Nev
    0.09
    çĸĻ
    0.09
    ä¹Łå°±æĺ¯
    0.09
    æ¶ķ
    0.09
    稼
    0.09
    Activations Density 0.002%

    No Known Activations