© 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. 2289
    Prev
    Next
    INDEX
    Explanations

    doingishasbeencontinuesprivatelyytotechnologymanhow

    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
    å©ī
    -0.08
    gent
    -0.08
    è¿Ļ件
    -0.08
    å¿Į
    -0.08
    第äºĮç§į
    -0.08
     Kol
    -0.08
    çĶļ
    -0.07
    rition
    -0.07
    åĪ¤å®ļ
    -0.07
    usive
    -0.07
    POSITIVE LOGITS
    积累äºĨ
    0.13
    èµ¢å¾ĹäºĨ
    0.12
    积累
    0.12
    积
    0.12
    åħ¨ä½ĵåijĺå·¥
    0.12
    稳åģ¥
    0.11
    ä¿¡èµĸ
    0.11
    ä¿¡èªī
    0.11
    å®ŀåĬĽ
    0.11
    åijĺå·¥
    0.11
    Activations Density 0.136%

    No Known Activations