© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9910
    Prev
    Next
    INDEX
    Explanations

    questions starting with "do"

    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
    ly
    -0.13
    nya
    -0.10
    ness
    -0.10
    ãģĦãģŁãĤī
    -0.10
    ãģĦãģ¾ãģĻ
    -0.10
    nu
    -0.09
    ael
    -0.09
    ONE
    -0.09
    anity
    -0.09
    å°¤åħ¶æĺ¯
    -0.09
    POSITIVE LOGITS
    xygen
    0.13
    ìį¨
    0.12
    ctype
    0.12
    ctrine
    0.12
    ÄŁ
    0.12
    è¿ĩçļĦ
    0.11
    笳
    0.11
    zent
    0.11
    ximity
    0.10
    æł·çļĦ
    0.10
    Activations Density 0.071%

    No Known Activations