© 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. 30207
    Prev
    Next
    INDEX
    Explanations

    see truly, abstract, dop

    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¨è¿Ļ
    -0.09
    失æݧ
    -0.08
    lad
    -0.08
    åľ¨æѤ
    -0.08
    æºĥ
    -0.08
     Hayward
    -0.08
    eds
    -0.08
     toll
    -0.08
    rief
    -0.08
     Provid
    -0.08
    POSITIVE LOGITS
    ä½ĵéªĮ
    0.18
    æĦŁåıĹ
    0.15
    é«Ķé©Ĺ
    0.15
    ä½ĵä¼ļ
    0.14
    亲身
    0.14
    æĦŁåıĹåĪ°
    0.14
    亲èĩª
    0.13
    亲
    0.13
    çļĦæĦŁåıĹ
    0.13
    ä½ĵä¼ļåĪ°
    0.12
    Activations Density 0.181%

    No Known Activations