© 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. 27092
    Prev
    Next
    INDEX
    Explanations

    quantitative analysis

    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
    æĪĴ
    -0.08
    [OF
    -0.08
     Rena
    -0.08
    å¼±
    -0.08
    orang
    -0.08
    wen
    -0.08
    æĢİä¹Ī说
    -0.08
    滥
    -0.08
    cdn
    -0.08
    å¥ijæľº
    -0.08
    POSITIVE LOGITS
    çij¶
    0.10
    ÙħÙĤ
    0.09
    åºĦæĿij
    0.09
    æŁı
    0.09
    å£ij
    0.09
    æĸ°å¼Ģ
    0.09
    缸åħ³æĸ°éĹ»
    0.09
    èĥ½è®©
    0.09
    髯
    0.08
    /Math
    0.08
    Activations Density 0.044%

    No Known Activations