© 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. 48967
    Prev
    Next
    INDEX
    Explanations

    to sign, to enhance, to your, you're, you're

    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
    è·ŁæĪij说
    -0.10
    own
    -0.10
    igo
    -0.09
    为èĩªå·±
    -0.09
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    éļıæŶéļıåľ°
    -0.08
    ç»Ļèĩªå·±
    -0.08
     own
    -0.08
    对æĪij说
    -0.08
    ยาว
    -0.08
    POSITIVE LOGITS
    æĤ¨
    0.12
    æĤ¨çļĦ
    0.11
     наÑĪиÑħ
    0.09
     você
    0.09
     ourselves
    0.09
    ä½łåľ¨
    0.09
    å±Ī
    0.08
     McA
    0.08
    æĪij们认为
    0.08
    eken
    0.08
    Activations Density 0.175%

    No Known Activations