© 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. 54727
    Prev
    Next
    INDEX
    Explanations

    game vs opponent

    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
    æķĿ
    -0.09
     contingency
    -0.09
    aits
    -0.09
    èµĦ
    -0.09
     zab
    -0.09
    .mb
    -0.09
    íĥĪ
    -0.09
    ç»Ń
    -0.08
    èijij
    -0.08
    åĬłæ²¹ç«Ļ
    -0.08
    POSITIVE LOGITS
    家éŨåı£
    0.10
    çĽij管éĥ¨éŨ
    0.09
    Fetch
    0.09
    ç³Ĭ
    0.09
    æķĮ人
    0.08
     Fetch
    0.08
    .fetch
    0.08
    ãĤıãĤĬ
    0.08
    对æīĭ
    0.08
    身边çļĦ
    0.08
    Activations Density 0.070%

    No Known Activations