© 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. 57047
    Prev
    Next
    INDEX
    Explanations

    get the better 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
    æİ¥åĪ°
    -0.10
    Sports
    -0.10
    纡
    -0.10
    æ¸ħåĩī
    -0.09
    å¯Ł
    -0.09
    æĿ¥åĽŀ
    -0.09
    æ³»
    -0.09
    è¿Ŀ
    -0.09
    fell
    -0.09
     Susp
    -0.09
    POSITIVE LOGITS
    ä¹±
    0.09
    çĽĹ
    0.09
    èĶĵ延
    0.09
    失æݧ
    0.09
     autonom
    0.09
    merce
    0.09
    太è¿ĩ
    0.08
    äºĤ
    0.08
    主宰
    0.08
    iken
    0.08
    Activations Density 0.073%

    No Known Activations