© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29628
    Prev
    Next
    INDEX
    Explanations

    fairy tales and princesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     paranoid
    -0.11
    inki
    -0.11
     Tup
    -0.11
     bons
    -0.11
     Antar
    -0.11
     lou
    -0.11
    /lab
    -0.11
     paranoia
    -0.10
     gim
    -0.10
    nal
    -0.10
    POSITIVE LOGITS
     Cinder
    0.33
     Fairy
    0.21
     fairy
    0.20
     prince
    0.18
     Prince
    0.18
     pumpkin
    0.17
    Prince
    0.16
     princes
    0.14
     transformation
    0.13
     Disney
    0.12
    Activations Density 0.120%

    No Known Activations