© 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. 10734
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    å¹ķ
    -0.10
     scars
    -0.09
    è¹Ī
    -0.09
    omap
    -0.08
    æīĵæĭ¼
    -0.08
    arring
    -0.08
    å¤ļ彩
    -0.08
    ANGLE
    -0.08
    tap
    -0.08
    _STS
    -0.08
    POSITIVE LOGITS
    人为
    0.09
    ernet
    0.09
    è¹ĩ
    0.09
    人群
    0.09
    ç¡®åĪĩ
    0.09
    æºIJæ³ī
    0.08
    æĬĢæľ¯æ°´å¹³
    0.08
    æĶ¿åĬ¡
    0.08
    羣å®ŀ
    0.08
    ä¸Ŀè·¯
    0.08
    Activations Density 0.052%

    No Known Activations