© 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. 17450
    Prev
    Next
    INDEX
    Explanations

    Ecma International

    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
     Vegas
    -0.09
    å´ĩ
    -0.09
    uv
    -0.08
    ä¿Ĺè¯Ŀ说
    -0.08
    maker
    -0.08
    edly
    -0.08
    åį´æĺ¯
    -0.08
    åIJ¯åıij
    -0.08
    urances
    -0.08
     pant
    -0.08
    POSITIVE LOGITS
    åı¨
    0.10
    主ä¹īèĢħ
    0.10
     minded
    0.10
    -minded
    0.09
    åĴĮåľ°åĮº
    0.09
    ä¹İ
    0.09
    merce
    0.09
    失è°ĥ
    0.08
    太ä¹ħ
    0.08
    ä»»ä½ķæŶåĢĻ
    0.08
    Activations Density 0.004%

    No Known Activations