© 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. 18396
    Prev
    Next
    INDEX
    Explanations

    study of

    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
    äºĨä¸Ģ个
    -0.12
     footage
    -0.11
     stuff
    -0.11
    çļĦä¸Ģ个
    -0.11
    们
    -0.10
    çļĦä¸Ģç§į
    -0.10
    etter
    -0.09
    ä¸Ģ个人
    -0.09
    stuff
    -0.09
    ä¸Ģ件äºĭæĥħ
    -0.09
    POSITIVE LOGITS
    quirer
    0.10
    åľ¨åºĬä¸Ĭ
    0.09
    çī¹åĪ«æĺ¯
    0.09
    çĦī
    0.09
    æѤ
    0.09
    主é¢ĺæ´»åĬ¨
    0.09
    å¦Ĥæľīä¾µæĿĥ
    0.08
    ystems
    0.08
    ymbols
    0.08
     Ñģебе
    0.08
    Activations Density 2.026%

    No Known Activations