© 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. 35337
    Prev
    Next
    INDEX
    Explanations

    of course, of the, of his

    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
    æݨèįIJéĺħ读
    -0.09
    导è´Ń
    -0.09
    æ¹ĥ
    -0.09
    åĵ¨
    -0.09
    åĩºçīĪ社
    -0.09
    åĴĮåľ°åĮº
    -0.09
    æĥķ
    -0.08
    bull
    -0.08
    åĩ«
    -0.08
    mare
    -0.08
    POSITIVE LOGITS
     reel
    0.10
    é¼ł
    0.10
    笥
    0.09
     reels
    0.09
    èĢĢ
    0.09
    riot
    0.09
    çķı
    0.08
    èĢ»
    0.08
    ono
    0.08
    åIJ¦
    0.08
    Activations Density 0.101%

    No Known Activations