© 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. 26416
    Prev
    Next
    INDEX
    Explanations

    poorly described living conditions

    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
    åı¯è§Ĥ
    -0.09
    eing
    -0.08
    轧
    -0.08
     Russo
    -0.08
    åįģ足
    -0.08
    åIJįåĪĹ
    -0.08
    ÅĪ
    -0.08
    åı²ä¸ĬæľĢ
    -0.08
    _RET
    -0.07
    å¤ķ
    -0.07
    POSITIVE LOGITS
    çĺ¼
    0.11
    è´«ç©·
    0.10
    èĦ±è´«
    0.10
    æĮ£æīİ
    0.10
    çªĺ
    0.10
    è´«åĽ°
    0.10
    ä¸įåłª
    0.10
    åĽ°
    0.10
    窮
    0.10
    ä»°
    0.10
    Activations Density 0.111%

    No Known Activations