© 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. 51234
    Prev
    Next
    INDEX
    Explanations

    immature age

    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
    溯
    -0.10
    hum
    -0.09
    忽
    -0.09
    ós
    -0.09
    èĩ´
    -0.09
    çķª
    -0.08
    æł·çļĦ
    -0.08
    èĴ¯
    -0.08
    åĺŁ
    -0.08
    èŁĴ
    -0.08
    POSITIVE LOGITS
    为人
    0.10
    æĬĬèĩªå·±çļĦ
    0.09
    èĭįçĻ½
    0.09
    çķ¸å½¢
    0.09
    åĬ³
    0.09
    .Nil
    0.08
    åĬ³åĬ¨
    0.08
    失败
    0.08
    åĭŀ
    0.08
     pathetic
    0.08
    Activations Density 0.074%

    No Known Activations