© 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. 55895
    Prev
    Next
    INDEX
    Explanations

    rows and columns

    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
    aal
    -0.10
    çªį
    -0.10
    çIJIJ
    -0.10
    æŁĶ软
    -0.09
    éĿĴå±±
    -0.09
    ลà¸ļ
    -0.09
    èģĭ
    -0.09
     Spicer
    -0.09
    笼
    -0.09
    å¢ŀåĢ¼
    -0.09
    POSITIVE LOGITS
    å±Ĥ
    0.11
     layer
    0.09
     layers
    0.09
    å±
    0.09
    纵
    0.09
    åıł
    0.09
    åłĨ
    0.09
    æĪĸå¤ļ
    0.09
    ä¸Ģè¡Į
    0.09
    èĨĿçĽĸ
    0.09
    Activations Density 0.218%

    No Known Activations