© 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. 49400
    Prev
    Next
    INDEX
    Explanations

    partly or partially

    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
    åı½
    -0.09
    大å¤ļ
    -0.09
    éĢĴ
    -0.09
    ĥģ
    -0.08
     nothing
    -0.08
    éģŀ
    -0.08
    _PW
    -0.08
    éĥ¢
    -0.08
    Į¨
    -0.08
    殿ä¸ĭ
    -0.08
    POSITIVE LOGITS
    isans
    0.10
    çĶļèĩ³æĺ¯
    0.10
    ä¹ĥèĩ³
    0.10
    çĶļèĩ³
    0.10
    çĶļèĩ³è¿ĺ
    0.10
    æıIJæĹ©
    0.09
    /full
    0.09
    wise
    0.09
    pur
    0.09
    è·Łä¸įä¸Ĭ
    0.09
    Activations Density 0.100%

    No Known Activations