© 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. 39428
    Prev
    Next
    INDEX
    Explanations

    by + company or project 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
    åħ³éĶ®æŶåĪ»
    -0.10
    æѤ
    -0.10
    еннÑĭй
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    ä¹ĥèĩ³
    -0.09
    ibly
    -0.09
    人士
    -0.09
    æľīå¿ħè¦ģ
    -0.09
    isbury
    -0.09
    éĢĭ
    -0.09
    POSITIVE LOGITS
    è¡·
    0.19
     virtue
    0.18
    gone
    0.17
    /on
    0.14
    /from
    0.14
    -products
    0.13
    -pass
    0.13
    -election
    0.13
    ç§įç§į
    0.12
     means
    0.12
    Activations Density 0.377%

    No Known Activations