© 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. 50279
    Prev
    Next
    INDEX
    Explanations

    years range

    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
    管çIJĨåĴĮ
    -0.10
    æī¿
    -0.09
    stry
    -0.09
    è´¨éĩıåĴĮ
    -0.09
    лин
    -0.08
    æī¿åıĹ
    -0.08
    sep
    -0.08
    åįģ大
    -0.08
    å¤Ħå¤Ħ
    -0.08
    eva
    -0.08
    POSITIVE LOGITS
    æ¶Įçİ°åĩº
    0.10
    åħ¶å®ĥ
    0.09
    amp
    0.09
    ç»Ń约
    0.09
    æĭ¬
    0.09
    ä¼ļåĩºçİ°
    0.09
    æ¶Įçİ°
    0.09
    èĩ³
    0.09
    æĬĵæįķ
    0.09
    æľīæĿ¡ä»¶çļĦ
    0.09
    Activations Density 0.149%

    No Known Activations