© 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. 40273
    Prev
    Next
    INDEX
    Explanations

    places to live

    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
    婵
    -0.10
    æ¿Ģ
    -0.09
    å¸ĪçĶŁ
    -0.09
    æĬķæĶ¾
    -0.08
    æĽĻåħī
    -0.08
    è¯īæ±Ĥ
    -0.08
    è°Ł
    -0.08
    æĮ¨
    -0.08
    é²ģ
    -0.08
    æĥŃ
    -0.08
    POSITIVE LOGITS
    æıIJåĩºçļĦ
    0.09
    侪
    0.09
    å±ħ家
    0.09
    èĭĮ
    0.09
    .utilities
    0.09
    usses
    0.09
    æ²IJæµ´
    0.08
    chip
    0.08
    çĨŁæĤīçļĦ
    0.08
     amore
    0.08
    Activations Density 0.071%

    No Known Activations