© 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. 48166
    Prev
    Next
    INDEX
    Explanations

    to an Description

    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
    æ·±å¤Ħ
    -0.09
    çħ§æł·
    -0.09
    个åĪ«
    -0.08
    ä¹ĭä½Ļ
    -0.08
    å¥
    -0.08
    å¾Ĺä½ı
    -0.08
    主æµģ
    -0.08
    4
    -0.08
    深度
    -0.07
    9
    -0.07
    POSITIVE LOGITS
    ør
    0.10
    _CODES
    0.10
    ä¸Ģç§į
    0.10
    贯彻èIJ½å®ŀ
    0.10
    åĮłå¿ĥ
    0.09
    该æ¡Ī
    0.09
    åģ¥åº·ç®¡çIJĨ
    0.09
    ervo
    0.09
    æľ¬æ¡Ī
    0.09
    åĹª
    0.09
    Activations Density 0.180%

    No Known Activations