© 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. 50021
    Prev
    Next
    INDEX
    Explanations

    Canon camera models

    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
    æĹ¶æ®µ
    -0.09
     пеÑĢи
    -0.09
    eme
    -0.08
    çīĮåŃIJ
    -0.08
    说ä¸įåĩº
    -0.08
    Hands
    -0.08
    uario
    -0.08
     dispersion
    -0.08
    çĸļ
    -0.08
    çĶŁäº§çĶŁæ´»
    -0.08
    POSITIVE LOGITS
    ÑģÑĤавка
    0.09
    èľ¡
    0.08
    èĿ¼
    0.08
    ек
    0.08
    geh
    0.08
    íĥij
    0.08
    .obtain
    0.08
     ARR
    0.08
    åIJ¦å®ļ
    0.08
    åıijåĩº
    0.08
    Activations Density 0.009%

    No Known Activations