© 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. 2103
    Prev
    Next
    INDEX
    Explanations

    governing bodies

    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
    mates
    -0.11
    ä¸ĢäºĽ
    -0.10
    ç²½
    -0.10
    çľĩ
    -0.10
    ownik
    -0.10
    inary
    -0.10
    å¾Īæ£Ĵ
    -0.09
    onom
    -0.09
    onomy
    -0.09
    ç²¾åĬĽ
    -0.09
    POSITIVE LOGITS
    éħįä¸Ĭ
    0.09
    ìĬµ
    0.08
    hey
    0.08
    éĩĮç¨ĭç¢ij
    0.08
    /pol
    0.08
    ä¼ļéķ¿
    0.08
    صاب
    0.08
    é¢Ĩè¢ĸ
    0.08
     AAC
    0.08
     lẽ
    0.08
    Activations Density 0.033%

    No Known Activations