© 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. 2249
    Prev
    Next
    INDEX
    Explanations

    k8s.io/apimachinery/v1

    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
    è¾ķ
    -0.10
    è¯Ĩ
    -0.09
    å¼ĢéŨ
    -0.09
    妣
    -0.09
    pData
    -0.09
    æķŀå¼Ģ
    -0.08
    ç®´
    -0.08
    èĢĥéªĮ
    -0.08
    å«īå¦Ĵ
    -0.08
    段
    -0.08
    POSITIVE LOGITS
    avl
    0.11
    ç´Ĭä¹±
    0.09
     ÑĢеÑĨеп
    0.08
    ä¸ĵèģĮ
    0.08
    alsa
    0.08
    æĿĢæīĭ
    0.08
    İ·
    0.08
    ä¸īåĪĨ
    0.08
    ä¸įä¸Ĭ
    0.08
    fter
    0.08
    Activations Density 0.196%

    No Known Activations