© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8942
    Prev
    Next
    INDEX
    Explanations

    obligation or requirement

    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
    樵
    -0.11
    èĮĦ
    -0.10
    RIORITY
    -0.09
    åİŁå§ĭ
    -0.09
    éĢĴ
    -0.09
    .rt
    -0.09
    ELLOW
    -0.09
    èł¹
    -0.09
    åħ¨èĩªåĬ¨
    -0.09
    rams
    -0.09
    POSITIVE LOGITS
    è´Ŀ壳
    0.09
    å¸ľ
    0.08
    æīĢ以说
    0.08
    认æ¸ħ
    0.08
     mandatory
    0.08
    ÑģÑĤвÑĥ
    0.08
    å±IJ
    0.08
     Echo
    0.08
    ses
    0.08
     collateral
    0.08
    Activations Density 0.064%

    No Known Activations