© 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. 56559
    Prev
    Next
    INDEX
    Explanations

    questions after punctuation

    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
    ä»İä¸Ń
    -0.12
    åľ¨åħ¶
    -0.10
    åľ¨æķ´ä¸ª
    -0.09
    ç½ijä¸Ĭ
    -0.09
    åľ¨è¿Ļ个
    -0.08
    沿çĿĢ
    -0.08
    åľ¨å¤ĸéĿ¢
    -0.08
    åľ¨çĶŁæ´»ä¸Ń
    -0.08
    åľ¨è¿Ļç§į
    -0.08
    åľ¨
    -0.08
    POSITIVE LOGITS
    /on
    0.10
    æł·åŃIJ
    0.10
    次æķ°
    0.10
    æ·Į
    0.09
    ãĤĴè¦ĭãģĽ
    0.09
    ä¸įçķĻ
    0.09
    éĤ£ä¹Īç®Ģåįķ
    0.09
    æ¥Ķ
    0.09
    楼
    0.09
    ernet
    0.09
    Activations Density 0.394%

    No Known Activations