© 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. 56040
    Prev
    Next
    INDEX
    Explanations

    window and blinds

    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
    ä½ĵ温
    -0.09
    ç©¿æĪ´
    -0.09
    ç¡Į
    -0.09
    å¥ĭæĪĺ
    -0.09
    å¾Ģåīį
    -0.09
    åīįçŀ»
    -0.09
    åĿŃ
    -0.09
    åľ»
    -0.08
    éĢĢåĽŀ
    -0.08
    èĢ³æľº
    -0.08
    POSITIVE LOGITS
    çªĹå¸ĺ
    0.12
    éģ®
    0.10
    çªĹæĪ·
    0.09
     blinds
    0.09
     Window
    0.09
     WINDOW
    0.09
     opener
    0.09
    (Window
    0.09
    Window
    0.09
     window
    0.09
    Activations Density 0.026%

    No Known Activations