© 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. 54469
    Prev
    Next
    INDEX
    Explanations

    percentage off

    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
     crest
    -0.10
    åIJĮæł·æĺ¯
    -0.09
     tent
    -0.09
    å¸IJ篷
    -0.09
    asley
    -0.09
    eer
    -0.09
    tent
    -0.09
    åľºæ¯ĶèµĽ
    -0.09
    oret
    -0.08
    åı²ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ocl
    0.10
    ys
    0.10
    .Features
    0.09
    çł»
    0.08
    CurrentUser
    0.08
    墨
    0.08
    äºĮçĻ¾
    0.08
    obi
    0.07
    æ³ł
    0.07
     reduction
    0.07
    Activations Density 0.024%

    No Known Activations