© 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. 27565
    Prev
    Next
    INDEX
    Explanations

    symptoms resolved or persisted

    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
    IDD
    -0.10
    ippi
    -0.10
    度è¿ĩ
    -0.09
    ORK
    -0.09
    æŁ¥çľĭåħ¨æĸĩ
    -0.09
    å¿ĥæĻº
    -0.09
    ä¹ĭ家
    -0.08
    æĢ¨
    -0.08
    æ¶Įçİ°
    -0.08
    平常
    -0.08
    POSITIVE LOGITS
    以人æ°ij
    0.09
    VERAGE
    0.09
    afen
    0.08
    æ¿Ĵ
    0.08
    cosa
    0.08
    å¦ĤæľŁ
    0.08
    -trash
    0.08
    åħ¨æµģç¨ĭ
    0.08
    Mock
    0.08
     DECL
    0.08
    Activations Density 0.112%

    No Known Activations