© 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. 23180
    Prev
    Next
    INDEX
    Explanations

    need to

    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
    æİ¥è¿ĩ
    -0.10
    è£ķ
    -0.09
    eto
    -0.09
    ä¹¾åĿ¤
    -0.09
    æĭį
    -0.08
    اض
    -0.08
    ä¸įå¾Ĺä¸į
    -0.08
    edList
    -0.08
    è¹Ĭ
    -0.08
     Dul
    -0.08
    POSITIVE LOGITS
    lessly
    0.12
    ovel
    0.10
    éĻķ
    0.10
    éĻĶ
    0.09
    æĩĤ
    0.09
    æľīèī²éĩijå±ŀ
    0.09
    è¿Ļ个æĹ¶ä»£
    0.08
    æ´»å¾Ĺ
    0.08
    .precision
    0.08
    代è¨Ģ人
    0.08
    Activations Density 0.042%

    No Known Activations