© 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. 38961
    Prev
    Next
    INDEX
    Explanations

    past participles like 'seen', 'spent', 'written'

    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
    äs
    -0.09
    inis
    -0.09
    æ¥
    -0.09
    åıijæī¬
    -0.09
    REW
    -0.09
     lắm
    -0.09
     دائÙħا
    -0.09
    OSE
    -0.09
    å¹³æŶ
    -0.08
    çłŃ
    -0.08
    POSITIVE LOGITS
    å±¥
    0.10
    éĻ¤æѤ
    0.10
     anything
    0.09
    ä¸ĢåĪ»
    0.09
    akin
    0.09
    éĿ¢çĽ®
    0.09
    èħķ
    0.09
    anything
    0.09
    æĹ¥å¤ľ
    0.09
    综åIJĪæĢ§
    0.09
    Activations Density 0.019%

    No Known Activations