© 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. 34586
    Prev
    Next
    INDEX
    Explanations

    when 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
    oku
    -0.10
    assa
    -0.09
    ï¸
    -0.09
    å°ıåŃIJ
    -0.09
    åĶ¯æľī
    -0.08
    æģķ
    -0.08
    åŃ°
    -0.08
    æ´¼
    -0.08
    éĤ¦
    -0.08
     pip
    -0.08
    POSITIVE LOGITS
    èĬ±éĴ±
    0.10
    nam
    0.09
    缸åıį
    0.09
    æĺİ天
    0.09
    窦
    0.09
    ocos
    0.08
    éĤ£æł·
    0.08
    åĻ¨å®ĺ
    0.08
    åĶ¿
    0.08
    ä¸ĸçķĮ第ä¸Ģ
    0.08
    Activations Density 0.019%

    No Known Activations