© 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. 27993
    Prev
    Next
    INDEX
    Explanations

    recent findings

    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
    éĽı
    -0.09
     hứng
    -0.09
    æĪĽ
    -0.09
    æĦıåIJij
    -0.09
    åĩ¡æĺ¯
    -0.09
    ÑģÑĤи
    -0.09
    æ§İ
    -0.08
    елÑı
    -0.08
    ToOne
    -0.08
     GPLv
    -0.08
    POSITIVE LOGITS
    éĩįæĸ°
    0.15
    çºłæŃ£
    0.14
    æīįåıijçİ°
    0.13
    åıijçİ°
    0.12
    å¤įæŁ¥
    0.12
    é¢łè¦Ĩ
    0.12
    æĽ´æĸ°
    0.11
    åıijçİ°äºĨ
    0.11
    ä¿®æŃ£
    0.11
     æĽ´æĸ°
    0.10
    Activations Density 0.147%

    No Known Activations