© 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. 11005
    Prev
    Next
    INDEX
    Explanations

    wireless communication or networks

    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
    .opensource
    -0.10
    ä½ĵä¼ļ
    -0.10
     Microsystems
    -0.10
    ç¾İåĽ¢
    -0.10
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.09
    ç¬ijèĦ¸
    -0.09
    getError
    -0.09
    egan
    -0.09
    larg
    -0.09
    åı¦ä¸ĢåįĬ
    -0.09
    POSITIVE LOGITS
     bargain
    0.08
    IGINAL
    0.07
    æľī两ç§į
    0.07
    åľ¨ç¾İåĽ½
    0.07
     hij
    0.07
    ÑĨенÑĤÑĢ
    0.07
     Gow
    0.07
    _VOLUME
    0.07
     eng
    0.07
     Windsor
    0.07
    Activations Density 1.636%

    No Known Activations