© 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. 39577
    Prev
    Next
    INDEX
    Explanations

    closing or closing down

    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
    å±Ĥå±Ĥ
    -0.09
    å¢ŀåĢ¼
    -0.08
    çµ®
    -0.08
    éķ¬
    -0.08
    ä¸ĵä¸ļ人士
    -0.08
    çŀ©çĽ®
    -0.08
    ugar
    -0.08
    ftime
    -0.08
    /Grid
    -0.08
    åıĭæĥħ
    -0.08
    POSITIVE LOGITS
    msp
    0.10
    对å¤ĸ
    0.09
    UEL
    0.09
     veins
    0.09
    人çĶŁ
    0.09
    æīĭä¸Ń
    0.09
    å¹ħ
    0.08
    nell
    0.08
    ela
    0.08
    è¿Ļä¸Ģ
    0.08
    Activations Density 0.027%

    No Known Activations