© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38504
    Prev
    Next
    INDEX
    Explanations

    cooking food

    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
    絾
    -0.09
    æ³ķåºŃ
    -0.08
    ç»ij
    -0.08
    æįĨç»ij
    -0.08
    ä¿®åīª
    -0.08
    astes
    -0.08
    æĭĪ
    -0.08
    sworth
    -0.08
    ecer
    -0.08
    å±Ĥåĩº
    -0.08
    POSITIVE LOGITS
    央
    0.10
    åĨ³èĥľ
    0.09
    çĥ¹
    0.09
    lesc
    0.09
    夫
    0.09
    æĶ¶å½ķ
    0.09
    æĻĴ
    0.08
    ç»ĻåĩºäºĨ
    0.08
    åī©ä¸ĭ
    0.08
    åĩĿ
    0.08
    Activations Density 0.027%

    No Known Activations