© 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. 62006
    Prev
    Next
    INDEX
    Explanations

    things that happened

    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
    éªĿ
    -0.11
    ÑģÑĥ
    -0.10
    人éĢī
    -0.10
    uet
    -0.10
    éĻŁ
    -0.09
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.09
    ocha
    -0.09
    åIJĮç±»
    -0.09
    dock
    -0.09
    éĥ¨åĪĨåĨħ容
    -0.09
    POSITIVE LOGITS
     happened
    0.14
     happening
    0.14
     happens
    0.13
     happen
    0.12
     Happ
    0.11
     пÑĢоиÑģ
    0.11
    诸å¦Ĥ
    0.11
     пÑĢоиÑģÑħодиÑĤ
    0.11
    å°ıå¾®
    0.11
    åģļçļĦ
    0.11
    Activations Density 0.324%

    No Known Activations