© 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. 55680
    Prev
    Next
    INDEX
    Explanations

    license agreements

    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
    åıijå±ķ空éĹ´
    -0.10
    æł¸ç®Ĺ
    -0.09
    åijĽ
    -0.09
    aira
    -0.09
    çŃ²
    -0.09
    rais
    -0.09
     Appeals
    -0.09
    attered
    -0.08
    ä¼ļ计
    -0.08
    (hidden
    -0.08
    POSITIVE LOGITS
    çŃ¾è®¢
    0.13
    çŃ¾ç½²
    0.12
     signed
    0.11
    ä¸Ģ份
    0.11
     agreements
    0.11
    ä¸īæĸ¹
    0.11
    åįıè®®
    0.10
     agreement
    0.10
    çŃ¾è®¢äºĨ
    0.10
    äºĨä¸Ģ份
    0.10
    Activations Density 0.232%

    No Known Activations