© 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. 16789
    Prev
    Next
    INDEX
    Explanations

    superhero and fictional characters

    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
    xec
    -0.09
    .toArray
    -0.09
    å·¥å§Ķ
    -0.09
     Interest
    -0.08
    鹿
    -0.08
    æī§
    -0.08
    enis
    -0.08
    åŃĻåŃIJ
    -0.08
    versation
    -0.08
    Projected
    -0.08
    POSITIVE LOGITS
    èĭ±éĽĦ
    0.13
    æĭ¯
    0.12
     hero
    0.11
     superhero
    0.11
    æĭħè´Ł
    0.10
    æķijåĬ©
    0.10
    hero
    0.10
    æķij人
    0.10
    (hero
    0.10
    èĭ±åĭĩ
    0.10
    Activations Density 0.137%

    No Known Activations