© 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. 48833
    Prev
    Next
    INDEX
    Explanations

    switching toARC or Ubuntu

    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
    ervo
    -0.10
    ittal
    -0.10
    ç»Ŀ大éĥ¨åĪĨ
    -0.09
    esy
    -0.09
    اض
    -0.09
    ä¹±
    -0.09
    -hole
    -0.09
    ChangeEvent
    -0.09
    خر
    -0.09
    ildo
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹Īæł·
    0.11
    æĸ°çļĦ
    0.10
    ä¸Ģ个æĸ°çļĦ
    0.09
    å½Ģ
    0.09
    æĽ´é«ĺçļĦ
    0.08
    ä½ķç§į
    0.08
    对她
    0.08
    æĪIJçĨŁçļĦ
    0.08
     grips
    0.08
    éĺµèIJ¥
    0.08
    Activations Density 0.087%

    No Known Activations