© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59353
    Prev
    Next
    INDEX
    Explanations

    describing research interests

    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
    Negative Logits
    æ¬Ĭ
    -0.09
    æīĭåĨĮ
    -0.09
    çīĪ
    -0.09
    æĸ°è§Ħ
    -0.09
    åĿĽ
    -0.08
    ç»´æĿĥ
    -0.08
    æĿĥéĻIJ
    -0.08
    çŃĸ
    -0.08
    getConfig
    -0.08
    ä»ĺè´¹
    -0.08
    POSITIVE LOGITS
    产ä¸ļåĮĸ
    0.08
    软
    0.08
    çĤĬ
    0.08
    计ç®Ĺæľº
    0.08
     даж
    0.08
    IEEE
    0.08
    velopment
    0.07
     backtrack
    0.07
    ä½ĵè´¨
    0.07
    loud
    0.07
    Activations Density 0.487%

    No Known Activations