© 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. 3557
    Prev
    Next
    INDEX
    Explanations

    comics and manga series 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
    Negative Logits
     Kling
    -0.13
     Lucas
    -0.10
     Snape
    -0.10
     Elemental
    -0.10
     dein
    -0.09
     blackmail
    -0.09
     hust
    -0.09
     Tib
    -0.09
     heater
    -0.09
     pref
    -0.08
    POSITIVE LOGITS
     Franken
    0.13
     Afro
    0.11
     killing
    0.11
     Gore
    0.11
     kills
    0.10
     Jackie
    0.10
     Razor
    0.10
     gore
    0.10
     Hunts
    0.10
     killed
    0.10
    Activations Density 0.359%

    No Known Activations