© 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. 39008
    Prev
    Next
    INDEX
    Explanations

    princess bride

    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
    æ¿
    -0.10
    uit
    -0.09
    å·¢
    -0.09
    å·´æĸ¯
    -0.09
    æģ©
    -0.09
    /private
    -0.08
    cola
    -0.08
    æĪ¢
    -0.08
    涯
    -0.08
    eras
    -0.08
    POSITIVE LOGITS
    æĹģ
    0.12
    åłĤ
    0.11
    MSN
    0.10
    omin
    0.09
    IRT
    0.09
    åĸĨ
    0.08
    æĭIJ
    0.08
    _BITS
    0.08
     ÑĢиÑģк
    0.08
    TRS
    0.08
    Activations Density 0.011%

    No Known Activations