© 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. 54857
    Prev
    Next
    INDEX
    Explanations

    this/these followed by verb

    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
    é¾Ļæ¹ĸ
    -0.08
    èĬŃ
    -0.08
     other
    -0.08
    åĪĥ
    -0.08
     thus
    -0.08
    è¿ĻæĿ¡
    -0.08
    è¿Ļ段
    -0.08
    è¿Ļåı¥è¯Ŀ
    -0.08
     therefore
    -0.08
    ationToken
    -0.08
    POSITIVE LOGITS
    éĥ½è¢«
    0.10
    éĩĮæĸ¯
    0.10
     Hort
    0.09
    èĦ©
    0.08
    æĸĹäºī
    0.08
     schem
    0.08
    Ñģен
    0.08
    交æį¢
    0.08
    chemy
    0.08
    âĬ¿
    0.08
    Activations Density 0.167%

    No Known Activations