© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16955
    Prev
    Next
    INDEX
    Explanations

    superhero or show titles

    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
     Jacksonville
    -0.11
    csi
    -0.10
     Cherokee
    -0.10
     Ort
    -0.10
     Sylv
    -0.10
     Nes
    -0.09
     ¶
    -0.09
    Province
    -0.09
     Magick
    -0.09
     Highlander
    -0.09
    POSITIVE LOGITS
     UA
    0.14
     Dek
    0.14
     Bak
    0.13
     hero
    0.12
     Ende
    0.12
     Explosion
    0.11
     quir
    0.11
     superhero
    0.11
     teammate
    0.11
     Kota
    0.11
    Activations Density 0.354%

    No Known Activations