© 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. 7171
    Prev
    Next
    INDEX
    Explanations

    disproportionate impact or risk

    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
    羣æŃ£çļĦ
    -0.09
     Rowe
    -0.09
    ç«ĭå¿Ĺ
    -0.09
    人ãĤĤ
    -0.09
    åĦĴ
    -0.08
    赢家
    -0.08
    ä¸į失
    -0.08
    妥
    -0.08
    ä½łæĥ³
    -0.08
    èı©æıIJ
    -0.08
    POSITIVE LOGITS
    å¾Ģå¾Ģæĺ¯
    0.10
    æĽ´å®¹æĺĵ
    0.09
    aley
    0.09
     Presenter
    0.09
    æľĢ容æĺĵ
    0.09
    äºİä¸Ģä½ĵ
    0.09
    å¾Ģå¾Ģ
    0.09
    inherits
    0.09
    夹
    0.09
    еÑģÑĤво
    0.08
    Activations Density 0.165%

    No Known Activations