© 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. 17229
    Prev
    Next
    INDEX
    Explanations

    Harry Potter characters and series

    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
     mage
    -0.10
     Dame
    -0.10
     Mage
    -0.10
     Royals
    -0.09
     Castle
    -0.09
    Mage
    -0.09
     Stalin
    -0.09
     Deus
    -0.09
     Fro
    -0.09
     Leipzig
    -0.09
    POSITIVE LOGITS
     Ginny
    0.17
     Moody
    0.16
     Percy
    0.15
     Ced
    0.14
     Fred
    0.13
     Ministry
    0.13
    Fred
    0.12
     Macy
    0.12
     Perc
    0.12
     Ruf
    0.12
    Activations Density 0.117%

    No Known Activations