© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    time or duration context

    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
    abbit
    -0.10
    å®ļæŶ
    -0.10
    ä¸ĩä¸Ģ
    -0.09
    寮
    -0.09
    æĪijåıĪ
    -0.09
    åĽŀäºĭ
    -0.09
    itor
    -0.09
    åŃĺåľ¨ä¸Ģå®ļ
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    UIS
    -0.08
    POSITIVE LOGITS
    åģľä¸ĭæĿ¥
    0.09
    aire
    0.09
     bada
    0.09
    帳
    0.08
    å°±è¿Ļä¹Ī
    0.08
    åIJ§
    0.08
    ç¾
    0.08
    onth
    0.08
    notice
    0.08
    ½æķ°
    0.08
    Activations Density 0.007%

    No Known Activations