© 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. 34010
    Prev
    Next
    INDEX
    Explanations

    support structures or equipment

    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
    åļ¼
    -0.09
    ÑĤоп
    -0.09
    ley
    -0.09
    å¸ĺ
    -0.09
    mant
    -0.09
    ä»ħ代表
    -0.08
    arkan
    -0.08
    æľīæĿ¡ä»¶çļĦ
    -0.08
    ISS
    -0.08
    weigh
    -0.08
    POSITIVE LOGITS
    稳
    0.12
    è´¢åĬ¡ç®¡çIJĨ
    0.09
    ç©©
    0.09
     Hats
    0.08
    _ARGUMENT
    0.08
    ä¹ĭåĬ¿
    0.08
    à¸Ĥา
    0.08
    ç¬Ĩ
    0.08
    MessageType
    0.08
    é«ĺçŃī
    0.08
    Activations Density 0.006%

    No Known Activations