© 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. 34768
    Prev
    Next
    INDEX
    Explanations

    this page or screen

    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
    ä¸Ģ次次
    -0.09
    æľīäºĽäºº
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.08
    7
    -0.08
    æŀķ
    -0.08
     Vaults
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.07
    åľ°çIJĥä¸Ĭ
    -0.07
    6
    -0.07
     Herman
    -0.07
    POSITIVE LOGITS
    éļıå¤Ħåı¯è§ģ
    0.10
    é«ĺ度éĩįè§Ĩ
    0.09
    麦
    0.09
     listings
    0.09
    éħ¢
    0.09
    ToFit
    0.09
    ToAdd
    0.09
    çĹĴ
    0.09
    æ©¡
    0.09
     sorts
    0.09
    Activations Density 0.018%

    No Known Activations