© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    to post

    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¸įç®¡ä½ł
    -0.09
    æīŃ
    -0.09
    caff
    -0.08
    ç¥Ģ
    -0.08
     tslint
    -0.08
    ATAR
    -0.08
    å¼Ģæľº
    -0.08
    ئ
    -0.08
    _rw
    -0.08
    å®ļä½į
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¹´ä¸Ģ度
    0.11
    ÙĦØ©
    0.09
     phạm
    0.09
    ä¸Ģå¹ħ
    0.09
    ç´łè´¨æķĻèĤ²
    0.08
    è¯Ŀ说
    0.08
    è´»
    0.08
    èĥŃ
    0.08
    æģŃ
    0.08
     recl
    0.08
    Activations Density 0.005%

    No Known Activations