© 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. 17527
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations

    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
    åIJĮè¡Į
    -0.11
    è¿Ļ个åIJįåŃĹ
    -0.09
    é£ŀç¿Ķ
    -0.09
    _ENCOD
    -0.08
    åľ¨å¤ĸ
    -0.08
    èĽĢ
    -0.08
    è¡°èĢģ
    -0.08
    æ´»ä¸ĭåİ»
    -0.08
    enas
    -0.08
    mer
    -0.08
    POSITIVE LOGITS
    åİ¥
    0.08
     ì·¨
    0.08
    ä¼ī
    0.08
    аÑĨиÑİ
    0.07
    ä¸Ģ度
    0.07
    å±ij
    0.07
    å±ħ
    0.07
    ìĭ
    0.07
    绶
    0.07
    _rom
    0.07
    Activations Density 0.186%

    No Known Activations