© 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. 5252
    Prev
    Next
    INDEX
    Explanations

    monks and monasteries

    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
    ä½ij
    -0.10
    åı¦ä¸ĢåįĬ
    -0.10
    主管éĥ¨éŨ
    -0.09
    课
    -0.09
    UDA
    -0.09
    izers
    -0.08
    ajs
    -0.08
    liner
    -0.08
    æŁĦ
    -0.08
    ัย
    -0.08
    POSITIVE LOGITS
    åĽ«
    0.09
    ç¹ĩ
    0.08
    íĿĶ
    0.08
    åħ¹
    0.08
    åĨħçļĦ
    0.08
    念
    0.08
     Bav
    0.08
    èķ²
    0.08
    angelo
    0.08
     Lik
    0.08
    Activations Density 0.022%

    No Known Activations