© 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. 6820
    Prev
    Next
    INDEX
    Explanations

    positions (seated, upright)

    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
    목
    -0.09
    ##_
    -0.08
    åĿĽ
    -0.08
    éŸ
    -0.08
    åıĺæĢģ
    -0.08
     Rew
    -0.08
    mpr
    -0.08
     물
    -0.08
    æģ¢å¤į
    -0.07
     Runner
    -0.07
    POSITIVE LOGITS
    æ¤ħåŃIJ
    0.13
    æ¤ħ
    0.13
    åĿIJ
    0.12
    æ¡Į
    0.11
    åĿIJçĿĢ
    0.11
    起身
    0.10
    å¸Ń
    0.10
    ç«Ļèµ·æĿ¥
    0.10
    座æ¤ħ
    0.10
    æĬĦè¢Ń
    0.10
    Activations Density 0.055%

    No Known Activations