© 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. 5438
    Prev
    Next
    INDEX
    Explanations

    sunday school

    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
    æĪ¾
    -0.10
    æİĮéŨ
    -0.10
    çıŀ
    -0.10
    èĺijèıĩ
    -0.10
    æŀģéĻIJ
    -0.09
     маÑģÑĤеÑĢ
    -0.09
    è¾¹éĻħ
    -0.09
    æĢ»è£ģ
    -0.09
    好äºĭ
    -0.09
    è±ĨèħIJ
    -0.08
    POSITIVE LOGITS
    enti
    0.09
    æ°Ķæ°Ľ
    0.09
     HOLDER
    0.08
    iod
    0.08
    AMY
    0.08
    _ability
    0.08
     Reception
    0.08
     xsi
    0.08
     Merkel
    0.08
    lete
    0.07
    Activations Density 0.008%

    No Known Activations