© 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. 53894
    Prev
    Next
    INDEX
    Explanations

    current or recent information

    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
    æĺ¨æĹ¥
    -0.10
    çļĦæĢģ度
    -0.10
    ä»İæĿ¥æ²¡æľī
    -0.10
    sov
    -0.09
    å±ĬæŶ
    -0.09
    èĢĮåĩº
    -0.09
    æĢģ度
    -0.09
     Ñģебе
    -0.09
    è¹´
    -0.09
    æľ¬æľŁ
    -0.09
    POSITIVE LOGITS
    oref
    0.09
    绣é¢Ĩ
    0.09
    zia
    0.09
    odem
    0.09
    aday
    0.08
    itol
    0.08
    éĽĨä¸Ń
    0.08
    clare
    0.08
    /live
    0.08
    umph
    0.08
    Activations Density 0.105%

    No Known Activations