© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7105
    Prev
    Next
    INDEX
    Explanations

    Mary names followed by last names

    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
    èIJ¥åķĨ
    -0.10
    çľĭä»ĸ
    -0.09
    西åĮĹ
    -0.09
    å°ıåŃIJ
    -0.09
    å·¥ä½ľç»Ħ
    -0.08
     Honest
    -0.08
    æħ¢
    -0.08
    ä»Ķç»Ĩ
    -0.08
     Steele
    -0.08
     Gä
    -0.08
    POSITIVE LOGITS
    å«Įçĸij
    0.08
    ç§ijæĬĢè¿ĽæŃ¥
    0.08
     traf
    0.08
    æºIJ头
    0.08
    wyn
    0.08
    bred
    0.08
    edith
    0.08
    .pipe
    0.08
    (SIG
    0.07
    常åĬ¡
    0.07
    Activations Density 0.145%

    No Known Activations