© 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. 5736
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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
    chas
    -0.09
    aven
    -0.09
    ç»Ģ
    -0.09
    agger
    -0.09
    бÑĢ
    -0.09
    lessons
    -0.08
    ä¹ī
    -0.08
    娲
    -0.08
    ETO
    -0.08
    计è¾ĥ
    -0.08
    POSITIVE LOGITS
    ãģªãĤĭ
    0.09
    nee
    0.08
    suspend
    0.08
    enheim
    0.08
     Chick
    0.08
     miser
    0.08
     Hib
    0.08
    -inner
    0.08
    ernel
    0.08
    nis
    0.08
    Activations Density 0.031%

    No Known Activations