© 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. 49080
    Prev
    Next
    INDEX
    Explanations

    wi-fi capability

    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
    åľ¨çĶŁæ´»ä¸Ń
    -0.10
    主æĦı
    -0.09
    æĴħ
    -0.09
     Urb
    -0.09
    ä»Ĩ
    -0.08
    (Mat
    -0.08
    zman
    -0.08
    ione
    -0.08
     Mat
    -0.08
     emotion
    -0.08
    POSITIVE LOGITS
    æĹłèģĬ
    0.11
    _PAD
    0.10
     Cabin
    0.10
    æĮĸ
    0.09
     Steele
    0.09
    ç»ıèIJ¥çIJĨ念
    0.09
    éĿĻéĿĻ
    0.09
    åĴ«
    0.09
    _busy
    0.09
    éĦĺ
    0.09
    Activations Density 0.078%

    No Known Activations