© 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. 57223
    Prev
    Next
    INDEX
    Explanations

    Team Kodi

    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
    ing
    -0.09
    å®ħ
    -0.09
    pek
    -0.09
    åľ¨æĪijçľĭæĿ¥
    -0.08
    çļĦæĪ¿åŃIJ
    -0.08
    æ¡ĥèĬ±
    -0.08
    åĨĻçĿĢ
    -0.08
    agg
    -0.08
    cio
    -0.08
    kest
    -0.08
    POSITIVE LOGITS
    ä¸ŃåĽ½åĪ¶éĢł
    0.10
    sville
    0.10
    åĬ¿åĬĽ
    0.09
    éºŁ
    0.09
    è´²
    0.09
    å¹²éĥ¨éĺŁä¼į
    0.09
    sis
    0.09
    æ¸ħæĸ°
    0.09
    isplay
    0.09
    ubi
    0.09
    Activations Density 0.154%

    No Known Activations