© 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. 57601
    Prev
    Next
    INDEX
    Explanations

    checkboxes and options

    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
    符åIJĪæĿ¡ä»¶
    -0.09
    æ½Ľ
    -0.08
    и
    -0.08
    éĴ¡
    -0.08
    ä¸įåıĬ
    -0.08
    uzzi
    -0.08
    éĻħ
    -0.08
    æŀĦæĪIJäºĨ
    -0.08
    æİĮ
    -0.08
    æĦıæĥ³ä¸įåĪ°
    -0.08
    POSITIVE LOGITS
    åĭ¾
    0.11
    åľ¨æİ¥åıĹ
    0.10
    æĬij
    0.09
    icl
    0.09
    lix
    0.09
    onica
    0.09
    æ±°
    0.09
     singleton
    0.09
    èĢĮåĩº
    0.09
    äººåľ¨
    0.09
    Activations Density 0.113%

    No Known Activations