© 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. 30571
    Prev
    Next
    INDEX
    Explanations

    sharing with you

    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
    icut
    -0.10
    绩
    -0.10
    缴å±ŀ
    -0.09
    ris
    -0.09
    ç»ĻåĪ«äºº
    -0.09
    è¸Ķ
    -0.09
    èŁĴ
    -0.09
    èĵį
    -0.09
    èİ«åIJį
    -0.09
    æĺ¼å¤ľ
    -0.09
    POSITIVE LOGITS
    们
    0.12
    åĢij
    0.10
    们çļĦ
    0.10
    -Feb
    0.08
    解æĶ¾
    0.08
     ali
    0.08
    æĻ´
    0.08
    shal
    0.08
    ioni
    0.08
    鸳
    0.08
    Activations Density 0.049%

    No Known Activations