© 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. 26544
    Prev
    Next
    INDEX
    Explanations

    get back to

    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
    uring
    -0.08
    æĥij
    -0.08
    ç¾ŀ
    -0.08
    çļĦ人çĶŁ
    -0.08
    èĢIJå¿ĥ
    -0.08
    交ä¼ļ
    -0.08
    lauf
    -0.08
    gan
    -0.08
    顽强
    -0.08
    FE
    -0.08
    POSITIVE LOGITS
    adel
    0.10
    itten
    0.10
    èĩ³äºİ
    0.09
     дело
    0.09
    lime
    0.09
    å¼¹
    0.09
    åĬŀçIJĨ
    0.09
    è¿Ļ件äºĭæĥħ
    0.09
    æİĴè¡Į
    0.09
    对ä»ĺ
    0.09
    Activations Density 0.040%

    No Known Activations