© 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. 33568
    Prev
    Next
    INDEX
    Explanations

    track and field events

    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
    æ¸ħæ·¡
    -0.10
    å·²ç»ı被
    -0.09
     Vig
    -0.09
    已被
    -0.09
    éĮ¾
    -0.09
    åĨįä¹Łä¸į
    -0.09
    èĦĸåŃIJ
    -0.09
    åħ±å»º
    -0.08
    æĭħ
    -0.08
    éĤ£å°±æĺ¯
    -0.08
    POSITIVE LOGITS
    éĹ»
    0.12
    èĬĴ
    0.10
    .ali
    0.09
    çĴŀ
    0.09
    Ä°K
    0.09
    èģŀ
    0.09
    çİ«çij°
    0.09
    roller
    0.09
    \API
    0.09
    æ²ģ
    0.09
    Activations Density 0.020%

    No Known Activations