© 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. 8316
    Prev
    Next
    INDEX
    Explanations

    Hemp Market

    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
    å±İ
    -0.09
    çī¹æĿĥ
    -0.09
    èŀĤ
    -0.09
    æī¹åıij
    -0.09
    sett
    -0.08
    å®ŀåľ¨æĺ¯
    -0.08
     Ritual
    -0.08
    зав
    -0.08
    .Pixel
    -0.08
     zest
    -0.08
    POSITIVE LOGITS
     interactive
    0.09
    讲座
    0.09
    å½ĵåľº
    0.08
    讲课
    0.08
    askan
    0.08
    fone
    0.08
    äºĴåĬ¨
    0.08
    å±ĬæŶ
    0.07
    å¿µä½Ľ
    0.07
    ä¸ĵåľº
    0.07
    Activations Density 0.133%

    No Known Activations