© 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. 3896
    Prev
    Next
    INDEX
    Explanations

    details

    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
    onto
    -0.09
    æĺĿ
    -0.08
    æĬ¥æ¡Ī
    -0.08
    ç§ijçłĶéĻ¢
    -0.08
    apsed
    -0.08
    éħ¥
    -0.08
    ontology
    -0.08
    æ¸ħæĸ°
    -0.08
    çī§åľº
    -0.08
     Bd
    -0.08
    POSITIVE LOGITS
    ä¹ĥ
    0.10
    isas
    0.09
    ç¸
    0.09
    å±ĭéĩĮ
    0.09
    çķĮçļĦ
    0.09
    isphere
    0.08
    解说
    0.08
    åĨįä¹Łæ²¡æľī
    0.08
    graf
    0.08
    ä¸Ģçķª
    0.08
    Activations Density 0.481%

    No Known Activations