© 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. 23750
    Prev
    Next
    INDEX
    Explanations

    chemical bond formation

    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
    atur
    -0.10
    çĶ¨å¿ĥ
    -0.09
    åįģä¸īå±Ĭ
    -0.09
    è¿Ļ个è¡Įä¸ļ
    -0.09
    æĢ»éĺŁ
    -0.09
    é¦Ĩ
    -0.09
     Beta
    -0.09
    åľ¨éĤ£éĩĮ
    -0.08
    ãĤıãĤĮ
    -0.08
     confl
    -0.08
    POSITIVE LOGITS
    骨
    0.10
    æĶ¥
    0.10
    å¥łåŁº
    0.10
    _cre
    0.09
    æļĿ
    0.09
    æ¡¥æ¢ģ
    0.09
    LOTS
    0.09
    溱
    0.09
    bone
    0.08
     Heck
    0.08
    Activations Density 0.626%

    No Known Activations