© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20048
    Prev
    Next
    INDEX
    Explanations

    infinite sequence, scroll, degree, stream, large

    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
    ../../../
    -0.10
    æĺ§
    -0.10
    NewLabel
    -0.09
    наÑĤ
    -0.09
    ðŁı»
    -0.09
    ä¸ĸ家
    -0.08
    ../../
    -0.08
     lãi
    -0.08
    ük
    -0.08
    iegel
    -0.08
    POSITIVE LOGITS
    -minded
    0.13
    åĮ¡
    0.10
    佬
    0.09
    zza
    0.09
    åĮ®
    0.09
    è¾±
    0.09
    çijķ
    0.09
    ç¥ļ
    0.09
    uess
    0.09
    涨
    0.08
    Activations Density 0.018%

    No Known Activations