© 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. 63647
    Prev
    Next
    INDEX
    Explanations

    fairy tale

    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
    çļĦç¾İ好
    -0.10
    èŀŃ
    -0.09
    ç¾İ好çļĦ
    -0.09
    ä¾Ĩ說
    -0.09
    ãĥªãĥ³ãĤ°
    -0.08
    HP
    -0.08
     tail
    -0.08
    æĪijçĪ±ä½ł
    -0.08
     joe
    -0.08
    åıijçİ°èĩªå·±
    -0.08
    POSITIVE LOGITS
    æŁIJ个
    0.13
    æŁIJç§į
    0.12
    è¦ģä¹Ī
    0.10
    ANTED
    0.10
    èĢĮéĿŀ
    0.10
    èĢĮä¸įæĺ¯
    0.10
    åĩºèĩª
    0.09
    产çī©
    0.09
    éļıæŶ
    0.09
    éļıæīĭ
    0.09
    Activations Density 0.058%

    No Known Activations