© 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. 39358
    Prev
    Next
    INDEX
    Explanations

    food additives and chemicals

    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
    驼
    -0.12
    ä¼ĹæīĢ
    -0.11
    å½¹
    -0.10
    amax
    -0.10
    æݺ
    -0.09
    åĩºåİĤ
    -0.09
    ä¸Ĭ课
    -0.09
    ä¸įä¸Ĭ
    -0.09
    untu
    -0.09
     louis
    -0.09
    POSITIVE LOGITS
    èĶ¬
    0.08
    çģŃçģ«
    0.08
    åIJĮåŁİ
    0.08
    æĶĺ
    0.08
    æĢı
    0.08
    ascus
    0.08
    æ¾į
    0.07
    è¿ĺæĥ³
    0.07
    åIJ¬è¯´
    0.07
    èľĢ
    0.07
    Activations Density 0.012%

    No Known Activations