© 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. 35518
    Prev
    Next
    INDEX
    Explanations

    same as or similar 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
    ä¸Ģå±Ĥ
    -0.09
    ä¸Ŀä¸Ŀ
    -0.09
    å¥Ħ
    -0.09
    راÙģ
    -0.09
    éĵ¸
    -0.08
    é«ĺé¢Ŀ
    -0.08
     ÑħоÑĤÑĮ
    -0.08
    è¶Ĭé«ĺ
    -0.08
    _stylesheet
    -0.08
    è¶Ĭå¤ļ
    -0.08
    POSITIVE LOGITS
    æĮģå¹³
    0.12
    å·®ä¸įå¤ļ
    0.11
    (equal
    0.10
    éķ¿çŁŃ
    0.10
    缸è¿ij
    0.10
    åĩºåħ¥
    0.10
    è¿Ľåĩº
    0.10
    çĶļèĩ³
    0.10
    çĶļèĩ³è¿ĺ
    0.09
    ä¹ĥèĩ³
    0.09
    Activations Density 0.140%

    No Known Activations