© 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. 30919
    Prev
    Next
    INDEX
    Explanations

    stay informed, keep up

    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
    åIJ¸å¼ķåĬĽ
    -0.10
    ç¼ĺ
    -0.08
    令
    -0.08
    cade
    -0.08
    andr
    -0.08
    anda
    -0.08
     ClassName
    -0.07
    å°Ĩ士
    -0.07
     fulfill
    -0.07
    åĪĽ
    -0.07
    POSITIVE LOGITS
    èİ·
    0.12
    ç±³åħ°
    0.10
    äºĨ解
    0.10
    é«Ń
    0.10
    èĩ³äºİ
    0.10
    çŀŃ解
    0.10
    çļĦåĬ¨ä½ľ
    0.09
    妥
    0.09
    置身
    0.09
     ÙħÙĪا
    0.09
    Activations Density 0.019%

    No Known Activations