© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8176
    Prev
    Next
    INDEX
    Explanations

    modal verbs and common phrases

    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
     exotic
    -0.09
     Andersen
    -0.08
    èĥĮåIJİçļĦ
    -0.08
    éĤĥ
    -0.08
    åı¨
    -0.08
    èĥĮåIJİ
    -0.08
    è¦ģçŁ¥éģĵ
    -0.08
    åĪ°åºķæĺ¯
    -0.08
    åĹŁ
    -0.08
    ippi
    -0.08
    POSITIVE LOGITS
    åĢĴæĺ¯
    0.11
    æīĵåĵį
    0.09
    æ´¾éģ£
    0.09
    DRAW
    0.09
    æµı
    0.09
    ngr
    0.08
    éĢĤ
    0.08
     Marvel
    0.08
    azon
    0.08
    iders
    0.08
    Activations Density 0.041%

    No Known Activations