© 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. 3201
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    mess
    -0.10
    ozy
    -0.10
    ëī´ìĬ¤
    -0.09
     miesz
    -0.09
    åħħåĪĨä½ĵçİ°
    -0.09
    orate
    -0.09
    æ·Ĩ
    -0.09
    第ä¸Ģä½į
    -0.09
    æīĭæİĮ
    -0.09
    åıªèĥ½è¯´
    -0.09
    POSITIVE LOGITS
    ä¸ĥæĺŁ
    0.10
    ä¸ĢæŃ¥æŃ¥
    0.09
    asin
    0.09
    éļıçĿĢæŶéĹ´
    0.08
     step
    0.08
    å¼Ģå±ķ
    0.08
    sync
    0.08
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.08
     martin
    0.08
     Artist
    0.08
    Activations Density 0.112%

    No Known Activations