© 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. 48304
    Prev
    Next
    INDEX
    Explanations

    world domination

    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
    åľ¨å¤ĸéĿ¢
    -0.09
    æŶéĹ´åĨħ
    -0.08
     ordinal
    -0.08
    壽
    -0.08
     Lifecycle
    -0.08
    essian
    -0.08
    ardi
    -0.07
    åľ¨ä»Ĭå¹´
    -0.07
    py
    -0.07
    èĢģå¸ĪçļĦ
    -0.07
    POSITIVE LOGITS
    ç´¯äºĨ
    0.13
    羡
    0.10
    isches
    0.10
    å»ĵ
    0.10
    è°İ
    0.09
    èĬĤèĥ½åĩıæİĴ
    0.09
    é¢ĨåĨĽ
    0.09
    æľ¬åľŁ
    0.09
    è§ĴèIJ½
    0.09
    /frontend
    0.09
    Activations Density 0.055%

    No Known Activations