© 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. 34191
    Prev
    Next
    INDEX
    Explanations

    last name followed by full name

    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
    è¿Ń
    -0.10
    <![
    -0.08
    秧
    -0.08
    èļĵ
    -0.08
    ож
    -0.08
    uyen
    -0.08
    å°ģ建
    -0.08
    严
    -0.08
    é²²
    -0.08
    å®ģ
    -0.08
    POSITIVE LOGITS
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.09
    æĪª
    0.09
    isha
    0.09
    æĴµ
    0.09
    çªģåĩ»
    0.09
    ä¸Ģè§Ĵ
    0.09
    elize
    0.09
    asha
    0.08
    çľ¯
    0.08
    ä¸ī项
    0.08
    Activations Density 0.021%

    No Known Activations