© 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. 27813
    Prev
    Next
    INDEX
    Explanations

    stone structures

    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
    寡
    -0.09
    åħħ满äºĨ
    -0.09
    æ²¹èĦĤ
    -0.09
    éķĢéĶĮ
    -0.09
    çĻ½ç³ĸ
    -0.08
    娼
    -0.08
    ãĤ·ãĤ¢
    -0.08
    .asc
    -0.08
    aux
    -0.08
     Ivory
    -0.08
    POSITIVE LOGITS
     sod
    0.10
    æ³¼
    0.09
    çīĩ
    0.09
    æĮª
    0.09
    åľ¨å½ĵåľ°
    0.09
    ç£Ĭ
    0.09
     ÑģпеÑĨиалÑĮно
    0.09
    丰
    0.08
    åľ¨åŃ¦æł¡
    0.08
    ä½ĵ积
    0.08
    Activations Density 0.051%

    No Known Activations