© 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. 33637
    Prev
    Next
    INDEX
    Explanations

    common

    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
    prung
    -0.10
    ä¸Ģåı·
    -0.09
    à¸ļรร
    -0.09
    æľ¨åľ°æĿ¿
    -0.08
    éŃħåĬĽ
    -0.08
    åĿŀ
    -0.08
    lop
    -0.08
    è¯Ĥ
    -0.08
    æĹ®
    -0.08
    ymbol
    -0.08
    POSITIVE LOGITS
    /common
    0.15
    /Common
    0.14
     common
    0.13
    (common
    0.13
    (Common
    0.13
    wealth
    0.13
     COMMON
    0.12
    .Common
    0.12
    常è§ģ
    0.11
     Common
    0.11
    Activations Density 0.162%

    No Known Activations