© 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. 18934
    Prev
    Next
    INDEX
    Explanations

    hear about / know what

    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
     Blackburn
    -0.10
    åŁ¹åħ»
    -0.10
    èµ·æŃ¥
    -0.09
    omat
    -0.09
    ä¸ĭæīĭ
    -0.08
    orm
    -0.08
    å´Ĩ
    -0.08
    åıijå±ķéĺ¶æ®µ
    -0.08
     DES
    -0.08
    å°ļ
    -0.08
    POSITIVE LOGITS
    大家åĪĨ享
    0.11
    ä½łä»¬
    0.11
    æĢĨ
    0.10
     ваÑĪи
    0.10
    ãģĤãģªãģŁãģ®
    0.10
    éĥ¨åī¯
    0.10
    ä»Ģä¹Īåij¢
    0.10
    æĺ¯æĢİæł·
    0.10
    eti
    0.10
    åĪ¶æľį
    0.09
    Activations Density 0.011%

    No Known Activations