© 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. 63151
    Prev
    Next
    INDEX
    Explanations

    can or could followed by a verb

    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
    åīįç½®
    -0.10
    enko
    -0.10
     Madd
    -0.09
     ØŃÙĪ
    -0.09
    owitz
    -0.09
    gary
    -0.09
    undy
    -0.09
    зал
    -0.09
    æĵ¦æĭŃ
    -0.09
    éľĵ
    -0.09
    POSITIVE LOGITS
    ç©¿æ¢Ń
    0.08
    éĴ
    0.08
    hum
    0.08
    èĺ§
    0.08
    å·¢
    0.08
    纵è§Ĥ
    0.08
     telesc
    0.08
    黳
    0.08
    æĦŁåıĹåĪ°äºĨ
    0.08
    è´«
    0.07
    Activations Density 0.453%

    No Known Activations