© 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. 19034
    Prev
    Next
    INDEX
    Explanations

    outlining and detailing

    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
    èī¯å¿ĥ
    -0.10
    å¾Ī大
    -0.10
    ä¸į大
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    _abort
    -0.09
    modifiable
    -0.09
    él
    -0.08
    çIJ®
    -0.08
    alk
    -0.08
    аÑĢа
    -0.08
    POSITIVE LOGITS
    ç§įç§į
    0.10
    å¦Ĥä½ķåİ»
    0.09
    å¦Ĥä½ķ
    0.09
    ç»°
    0.09
    ä»Ģä¹Īæĺ¯
    0.09
    éĻĭ
    0.09
    ä¸Ģçķª
    0.09
     اÙĦÙħÙħÙĦ
    0.09
    ennes
    0.09
     how
    0.09
    Activations Density 0.034%

    No Known Activations