© 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. 2390
    Prev
    Next
    INDEX
    Explanations

    access to

    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
    ä¸ĵåįĸåºĹ
    -0.10
    avit
    -0.09
    åĩ¿
    -0.09
    erate
    -0.09
    èĪĮå°ĸ
    -0.09
    ä¸Ģ群
    -0.09
    åı¯ä»¥èİ·å¾Ĺ
    -0.09
    ç¾¹
    -0.09
    rollers
    -0.09
    è´¨åľ°
    -0.09
    POSITIVE LOGITS
    kul
    0.09
     via
    0.09
    èĩªå®¶
    0.09
    udy
    0.08
    æŶä¸į
    0.08
    ible
    0.08
     Freeman
    0.08
     dise
    0.08
    IBLE
    0.08
    _SDK
    0.08
    Activations Density 0.020%

    No Known Activations