© 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. 23738
    Prev
    Next
    INDEX
    Explanations

    quoted speech start

    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
    æķŀ
    -0.09
    _ctxt
    -0.08
    ãĤ«ãĥ¼
    -0.08
    usb
    -0.08
    ä¼¢
    -0.08
    ê°ij
    -0.08
    éģĤ
    -0.08
    ê·¹
    -0.08
     Ped
    -0.08
    eref
    -0.08
    POSITIVE LOGITS
    è°ģèĥ½
    0.10
    被çĽĹ
    0.09
    è¿Ļæĺ¯æĪij
    0.09
    è°ģçŁ¥éģĵ
    0.09
    iming
    0.08
    æĤł
    0.08
    ä¸ĢåĪĨ
    0.08
    漫
    0.08
     mang
    0.08
    rup
    0.08
    Activations Density 0.032%

    No Known Activations