© 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. 2384
    Prev
    Next
    INDEX
    Explanations

    interpret understanding context

    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
    igram
    -0.09
    åľ¨æĪij
    -0.08
    licit
    -0.08
    æĺİç¡®æıIJåĩº
    -0.08
    æĸ§
    -0.08
    Pri
    -0.08
     Priest
    -0.08
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.08
    iform
    -0.08
    avings
    -0.08
    POSITIVE LOGITS
    MenuBar
    0.10
    çŁ¥æĥħ
    0.10
    æİĮæı¡
    0.10
    emet
    0.09
    пÑĢÑı
    0.09
    è¿©
    0.09
    鹿
    0.09
    æİĮæı¡äºĨ
    0.09
    liner
    0.09
    ÑĨиÑı
    0.09
    Activations Density 0.021%

    No Known Activations