© 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. 17168
    Prev
    Next
    INDEX
    Explanations

    opening up or the opening of

    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
    æģ°å¥½
    -0.12
    åĪļ好
    -0.10
    æŃ£å¥½
    -0.10
    à¸ķรา
    -0.10
     má»ĩnh
    -0.09
    л
    -0.09
    æļĤ
    -0.09
    æ´ĭ
    -0.09
    Ñģко
    -0.09
    follower
    -0.09
    POSITIVE LOGITS
    ç¹ģå¿Ļ
    0.09
    /rs
    0.09
     Elem
    0.08
    æĴµ
    0.08
    ilk
    0.08
    æĢµ
    0.08
    éķ¿éķ¿çļĦ
    0.08
    éļĻ
    0.08
    isen
    0.08
    нÑĮ
    0.08
    Activations Density 0.011%

    No Known Activations