© 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. 48283
    Prev
    Next
    INDEX
    Explanations

    physics engine or world

    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
    楣
    -0.09
    两ä½į
    -0.09
    steller
    -0.09
    çĶµç«Ļ
    -0.09
    ç«ĻçĿĢ
    -0.09
    åģı离
    -0.09
    ç¿ĺ
    -0.09
     Madden
    -0.09
    ings
    -0.08
    oit
    -0.08
    POSITIVE LOGITS
    æIJŀ好
    0.09
    ä¿
    0.09
     Scout
    0.09
     finely
    0.09
    etti
    0.09
    etter
    0.08
    ä¾ĭè¡Į
    0.08
     вÑĭÑģоко
    0.08
    ctr
    0.08
    满
    0.08
    Activations Density 0.027%

    No Known Activations