© 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. 34112
    Prev
    Next
    INDEX
    Explanations

    product reviews

    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
     tours
    -0.10
     tour
    -0.10
    -0.10
    OfWork
    -0.09
    çŁŃçŁŃ
    -0.09
    顺德
    -0.09
    éĺģ
    -0.09
    éķĿ
    -0.09
    åĩ³
    -0.09
    éķĹ
    -0.09
    POSITIVE LOGITS
    ä¸Ģå¥Ĺ
    0.10
    éļľ
    0.09
    pose
    0.09
    /products
    0.08
    èĵĬ
    0.08
    çĻ»
    0.08
    sWith
    0.08
    åIJį家
    0.08
    actionDate
    0.08
    thouse
    0.08
    Activations Density 0.013%

    No Known Activations