© 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. 29603
    Prev
    Next
    INDEX
    Explanations

    armor, armour, fortified

    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
    å¸ľ
    -0.10
    боÑĢ
    -0.09
    èĭ¹
    -0.09
    ç«Ļéķ¿
    -0.09
    æŃ£åĢ¼
    -0.09
    å¸Ĩ
    -0.09
     parm
    -0.09
    fur
    -0.09
    èĥ¡åŃIJ
    -0.09
    éºĤ
    -0.08
    POSITIVE LOGITS
    ered
    0.10
    aic
    0.09
    edList
    0.09
    æĨ¨
    0.09
    anic
    0.09
    æij§
    0.09
    _RANK
    0.08
    æĭ¯
    0.08
    ण
    0.08
    QualifiedName
    0.08
    Activations Density 0.007%

    No Known Activations