© 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. 57977
    Prev
    Next
    INDEX
    Explanations

    in some way

    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
    çī¢
    -0.09
     Jacqu
    -0.09
    worth
    -0.08
    æįı
    -0.08
    TPL
    -0.08
    tor
    -0.08
    å¾Ĺèµ·
    -0.08
     TB
    -0.08
    igh
    -0.08
    TB
    -0.08
    POSITIVE LOGITS
     ways
    0.15
    çļĦæĸ¹å¼ı
    0.14
     way
    0.14
    æĸ¹å¼ı
    0.13
    çļĦæĸ¹å¼ıæĿ¥
    0.12
     Ways
    0.12
     manière
    0.12
     manner
    0.11
    WAYS
    0.10
    å¾Īéĩįè¦ģçļĦ
    0.10
    Activations Density 0.065%

    No Known Activations