© 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. 54904
    Prev
    Next
    INDEX
    Explanations

    little

    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
    ä¹ĭ声
    -0.11
    åľ°éģĵ
    -0.10
    èį·
    -0.10
    steen
    -0.10
    çķĪ
    -0.09
    æİł
    -0.09
    éĶ¢
    -0.09
    æľīåºıæİ¨è¿Ľ
    -0.09
    åĪĨæĺİ
    -0.09
    çī©åĵģ
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĤ¹
    0.10
    èįī
    0.09
     bit
    0.08
    æ»´æ»´
    0.08
    -known
    0.08
    naire
    0.08
    ipop
    0.08
    ä¹Łä¸įéĶĻ
    0.08
    beck
    0.08
    ÑĩиÑģлен
    0.08
    Activations Density 0.048%

    No Known Activations