© 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. 4253
    Prev
    Next
    INDEX
    Explanations

    first time in

    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
    åıªåī©ä¸ĭ
    -0.10
    éĤ£æŶåĢĻ
    -0.10
     اÙĦÙĤر
    -0.09
    ä¸Ĭåı¸
    -0.09
    åī©ä¸ĭ
    -0.09
    âĨĸ
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.09
    -transitional
    -0.09
    _hop
    -0.09
    åī©
    -0.08
    POSITIVE LOGITS
    éĩįä»»
    0.09
    建ç«ĭèµ·
    0.08
    å°ıç¼ĸ
    0.08
    åIJĪæĪIJ
    0.08
     anim
    0.08
    åIJİèĢħ
    0.08
    åįĬæľĪ
    0.08
     Barney
    0.08
    åħħåĪĨä½ĵçİ°
    0.07
    0.07
    Activations Density 0.021%

    No Known Activations