© 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. 39403
    Prev
    Next
    INDEX
    Explanations

    right now

    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
    åĴ¤
    -0.09
    âĿĸ
    -0.09
    Pane
    -0.09
    [color
    -0.09
    é¼Ļ
    -0.08
    à¸ŀา
    -0.08
    è¿ĩéĶĻ
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    heads
    -0.08
     sẵ
    -0.08
    POSITIVE LOGITS
    å·¡è§Ĩ
    0.10
    èĮ¬
    0.09
    漪
    0.09
    zar
    0.09
    wards
    0.09
    ilies
    0.09
     DSL
    0.08
    tings
    0.08
    iness
    0.08
    ierarchical
    0.08
    Activations Density 0.011%

    No Known Activations