© 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. 18603
    Prev
    Next
    INDEX
    Explanations

    IT design and technology

    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
    ä¸Ĭæ¦ľ
    -0.10
    æīĵæĸŃ
    -0.09
    åį«è§Ĩ
    -0.09
    GAN
    -0.09
     Tooth
    -0.08
    éĶĦ
    -0.08
    èĢķ
    -0.08
    ç»ıèIJ¥çIJĨ念
    -0.08
    è¯Ŀè¯Ń
    -0.08
    manuel
    -0.08
    POSITIVE LOGITS
    é¡¹çĽ®å»ºè®¾
    0.10
    èĦ±
    0.10
     IT
    0.09
    æĶ¹éĢł
    0.09
     жид
    0.09
     rum
    0.09
    vendors
    0.09
    çĥŁåĽ±
    0.09
     Pais
    0.09
    åľ¨è¿ĩ渡
    0.08
    Activations Density 0.121%

    No Known Activations