© 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. 55683
    Prev
    Next
    INDEX
    Explanations

    just, exactly, very

    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
    éŀŃ
    -0.10
    enheim
    -0.10
    æį¢
    -0.10
    åij·
    -0.09
    é¦Ļ
    -0.09
    å½¢
    -0.08
    å¼±
    -0.08
    ä¸Ģéģĵ
    -0.08
    _CONNECT
    -0.08
    .tpl
    -0.08
    POSITIVE LOGITS
    æŃ£æĺ¯
    0.25
    æģ°æģ°
    0.23
    ä¹ŁæŃ£æĺ¯
    0.22
     exactly
    0.17
     именно
    0.17
    æģ°å¥½
    0.17
     precisely
    0.16
    æŃ£æĺ¯åĽłä¸º
    0.16
     Ðĺменно
    0.15
    æŃ£å¥½
    0.15
    Activations Density 0.033%

    No Known Activations