© 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. 11900
    Prev
    Next
    INDEX
    Explanations

    coupon code or discounts

    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
    踵
    -0.11
    odata
    -0.08
    물ìĿĦ
    -0.08
     меÑĢ
    -0.08
    æ²¹çĶ°
    -0.08
    çĭłæĬĵ
    -0.08
    çļ¿
    -0.08
    驹
    -0.08
    rowse
    -0.08
    leep
    -0.08
    POSITIVE LOGITS
    大åħ¨
    0.11
    holders
    0.10
    ishly
    0.10
    اتÙĩا
    0.09
    æĮģæľī人
    0.09
     HOLDER
    0.09
    âĸ»
    0.09
    thouse
    0.09
    åĤ¥
    0.09
    IFY
    0.09
    Activations Density 0.002%

    No Known Activations