© 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. 27029
    Prev
    Next
    INDEX
    Explanations

    Drew Time, Ramirez Rodriguez

    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
    keh
    -0.10
    é¹°
    -0.10
    夺
    -0.09
    æ¸ħåĩī
    -0.09
    omics
    -0.09
    æݼ
    -0.09
    UL
    -0.09
    åĮłå¿ĥ
    -0.09
    çīĪæĿĥæīĢæľī
    -0.09
    old
    -0.08
    POSITIVE LOGITS
     lÆ°Æ¡ng
    0.10
    èĥİ
    0.10
    èī¯
    0.10
     Affero
    0.09
    ä¸ŀ
    0.09
    -git
    0.09
    è¯Ĩ
    0.09
    зов
    0.08
    git
    0.08
     git
    0.08
    Activations Density 0.018%

    No Known Activations