© 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. 22769
    Prev
    Next
    INDEX
    Explanations

    types of

    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
     Favorites
    -0.08
     quarter
    -0.08
     clr
    -0.08
    åı¦
    -0.08
    Å«
    -0.08
    è¿Ļç§į
    -0.07
    åĮºåŁŁåĨħ
    -0.07
    æŶä¸į
    -0.07
    wed
    -0.07
     пÑĢид
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.11
    æ»Ķ
    0.11
    ppers
    0.10
     гол
    0.10
    çļĦåıijçĶŁ
    0.10
    нÑĭ
    0.09
    çļĦæĦŁåıĹ
    0.09
    çļĦç»ıéªĮ
    0.09
    åIJĦèĩª
    0.09
    éĢł
    0.09
    Activations Density 0.099%

    No Known Activations