© 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. 10760
    Prev
    Next
    INDEX
    Explanations

    left to

    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
    ÑĥлÑĮ
    -0.11
    nev
    -0.09
    çīµ
    -0.09
    åĶ±
    -0.09
    åĨįè§ģ
    -0.08
     одеж
    -0.08
    sdk
    -0.08
     кÑĢÑĥ
    -0.08
     ÙĪÙħع
    -0.08
    axe
    -0.08
    POSITIVE LOGITS
    çļĦæŶåĢĻ
    0.09
    åĿıäºĨ
    0.09
    樽
    0.09
    æķijæµİ
    0.09
    æħ¢æħ¢
    0.08
     nhiá»ħm
    0.08
    cket
    0.08
     discretion
    0.08
    æݨæµĭ
    0.08
    æĥŃ
    0.08
    Activations Density 0.009%

    No Known Activations