© 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. 47700
    Prev
    Next
    INDEX
    Explanations

    self or personal reflection

    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
    åİĨåı²æĤłä¹ħ
    -0.10
    èĥ½åĬĽå¼º
    -0.09
    ä¼ĹæīĢ
    -0.09
    ä¹ħ
    -0.09
    å®ĺ
    -0.09
    èµĽåIJİ
    -0.09
    çªģå¦Ĥåħ¶æĿ¥
    -0.09
    亿ä¸ĩ
    -0.09
    çİ°å®ŀä¸Ń
    -0.09
    æĥ³åĪ°äºĨ
    -0.08
    POSITIVE LOGITS
    轨
    0.11
    æ¡£
    0.10
    åijµ
    0.10
    ZIP
    0.09
    odi
    0.09
    å½ĵåĪĿ
    0.09
    odel
    0.09
    çĴĭ
    0.09
    .nc
    0.08
    .datab
    0.08
    Activations Density 0.034%

    No Known Activations