© 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. 20078
    Prev
    Next
    INDEX
    Explanations

    communication and contact information

    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
    æ´¾
    -0.11
     Scotia
    -0.10
    ä¹ĭä½ľ
    -0.10
    äºĨ许å¤ļ
    -0.10
    ç¼ļ
    -0.10
    èī²æĥħ
    -0.10
    工夫
    -0.10
    ä¼IJ
    -0.10
    ething
    -0.10
    大家éĥ½åľ¨
    -0.10
    POSITIVE LOGITS
    仲
    0.08
    BaseContext
    0.08
    Ñĭва
    0.07
    ving
    0.07
    rus
    0.07
     blink
    0.07
    ì°Į
    0.07
    FUNC
    0.07
    ä½Ļ
    0.07
    sek
    0.07
    Activations Density 0.363%

    No Known Activations