© 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. 49485
    Prev
    Next
    INDEX
    Explanations

    Tarrant County

    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
    ä¹Ŀæ±Ł
    -0.14
    .getAs
    -0.10
    æ²¼
    -0.10
    森
    -0.09
    æĶ¶è´¹æłĩåĩĨ
    -0.09
     gaussian
    -0.09
    ILLED
    -0.09
    æ·®åįĹ
    -0.09
    åĹŁ
    -0.09
    é»Ħæ²³
    -0.09
    POSITIVE LOGITS
    æ©ĩ
    0.09
    ople
    0.09
     VC
    0.08
    /ext
    0.08
    gies
    0.08
    åģļ人
    0.08
     Mercy
    0.08
    贷款
    0.08
    åħ¶ä¸ŃåĮħæĭ¬
    0.08
     Cortex
    0.08
    Activations Density 0.317%

    No Known Activations