© 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. 5664
    Prev
    Next
    INDEX
    Explanations

    arrangement of items or subjects

    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
    大åݦ
    -0.09
    æµ·å²Ľ
    -0.09
    çŃĸåĪĴ
    -0.08
     ful
    -0.08
    å¥ĸåĬ±
    -0.08
     tenants
    -0.08
    槿
    -0.08
    å¹¹
    -0.08
    ä¸ĩ人
    -0.08
     building
    -0.08
    POSITIVE LOGITS
    èµ°åľ¨
    0.15
    åīįéĿ¢
    0.14
    é¢Ĩè·ij
    0.13
    åīįåĪĹ
    0.13
    带éĺŁ
    0.13
    åīįè¡Į
    0.13
    éĺŁä¼į
    0.12
    è¡ĮåĪĹ
    0.12
     ìķŀ
    0.12
    åħĪè¡Į
    0.12
    Activations Density 0.060%

    No Known Activations