© 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. 31445
    Prev
    Next
    INDEX
    Explanations

    compiled lists

    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
    åĬ¨æijĩ
    -0.10
    åģ¥
    -0.10
    æµģæĺŁ
    -0.09
    ãģĭãģĭãĤĭ
    -0.09
    leh
    -0.09
    æľīçļĦ
    -0.09
    幸
    -0.09
    reet
    -0.09
    广åijĬæľįåĬ¡
    -0.08
    åIJ±
    -0.08
    POSITIVE LOGITS
    æķ´çIJĨ
    0.12
    èĢĮæĪIJ
    0.11
     gather
    0.10
     gathering
    0.10
    semble
    0.09
    å½Ĵ纳
    0.09
     ÑģпиÑģок
    0.09
    äºĨä¸Ģ份
    0.09
    座ä½į
    0.09
    èµ·æĿ¥
    0.09
    Activations Density 0.045%

    No Known Activations