© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52989
    Prev
    Next
    INDEX
    Explanations

    change and flexibility

    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
    ofday
    -0.09
     ÑģовеÑĢ
    -0.09
    å¹³åİŁ
    -0.09
    .memo
    -0.09
    å·´å·´
    -0.08
    imension
    -0.08
    akis
    -0.08
    orne
    -0.08
    åıĮåıĮ
    -0.08
    å·¥ä¸ļ
    -0.08
    POSITIVE LOGITS
    ä»ĬåIJİ
    0.13
    å°ĨæĿ¥
    0.13
     future
    0.12
    éļıæŶ
    0.12
    以åIJİ
    0.12
    æľªæĿ¥
    0.12
    æĹ¥åIJİ
    0.12
    åľ¨æľªæĿ¥
    0.12
    future
    0.12
     later
    0.12
    Activations Density 0.184%

    No Known Activations