© 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. 34470
    Prev
    Next
    INDEX
    Explanations

    freshly prepared ingredients

    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
    çĻ½èıľ
    -0.10
    ä¸Ģåı¥
    -0.09
    pire
    -0.09
    诣
    -0.09
    éºĭ
    -0.09
    æħ°
    -0.09
    ä¸Ģå¹´ä¸Ģ度
    -0.09
    缸è§ģ
    -0.08
    ((__
    -0.08
    ä¸Ģ人
    -0.08
    POSITIVE LOGITS
    æĶ¹éĿ©åĪĽæĸ°
    0.09
    ogn
    0.08
    éĹ°
    0.08
    æľĭ
    0.08
    è°ĥ
    0.07
     McGr
    0.07
    é»ı
    0.07
    ãģĻãģ¹
    0.07
    å¥ij约
    0.07
    etz
    0.07
    Activations Density 0.014%

    No Known Activations