© 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. 54090
    Prev
    Next
    INDEX
    Explanations

    WW compounds

    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
    绾
    -0.09
    çļĦè·¯ä¸Ĭ
    -0.09
    iry
    -0.08
     Rubio
    -0.08
    æīŃ
    -0.08
    adem
    -0.08
    yps
    -0.08
    peg
    -0.08
    沿海
    -0.08
    opsis
    -0.08
    POSITIVE LOGITS
    abouts
    0.10
    inely
    0.09
    á»ģ
    0.09
    请åıĬæŶ
    0.09
    allis
    0.09
    obe
    0.09
     cous
    0.09
    é®
    0.08
    ipl
    0.08
    æĪĺæľ¯
    0.08
    Activations Density 0.002%

    No Known Activations