© 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. 23509
    Prev
    Next
    INDEX
    Explanations

    names starting with i, a, or numbers

    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
    æĶ¾å¿ĥ
    -0.08
     Downing
    -0.08
     fore
    -0.08
    çıŀ
    -0.08
    rops
    -0.08
     bounded
    -0.08
    秦
    -0.08
    èľķ
    -0.08
    æĽ´å¤ļ精彩
    -0.08
    è¿Ļçīĩ
    -0.08
    POSITIVE LOGITS
     Bol
    0.10
    bol
    0.10
    å¹´åºķåīį
    0.09
    ä¹¾éļĨ
    0.09
    ierarchical
    0.08
    olian
    0.08
    讦
    0.08
    ply
    0.08
    acci
    0.08
     Bolt
    0.08
    Activations Density 0.102%

    No Known Activations