© 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. 26605
    Prev
    Next
    INDEX
    Explanations

    progress speed or schedule

    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
    çªģ
    -0.09
    æıĨ
    -0.09
    -Sah
    -0.09
     повÑĭ
    -0.09
    æīįç®Ĺ
    -0.09
    æıIJ
    -0.08
    裸
    -0.08
     Blink
    -0.08
    åĪ«äºº
    -0.08
    åī¯æĢ»
    -0.08
    POSITIVE LOGITS
    yk
    0.09
    ilet
    0.09
    æĸ°çļĦä¸Ģå¹´
    0.09
    ä¸Ńç§ĭèĬĤ
    0.09
    没éĶĻ
    0.09
     weekly
    0.08
    çĶµéĩı
    0.08
    åŁł
    0.08
    nder
    0.08
    weekly
    0.08
    Activations Density 0.008%

    No Known Activations