© 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. 25841
    Prev
    Next
    INDEX
    Explanations

    Riverdale characters

    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
     cub
    -0.11
     cube
    -0.10
     cubes
    -0.10
    foon
    -0.09
     sf
    -0.09
     Cube
    -0.09
    _cube
    -0.09
     Boeing
    -0.09
     Nathan
    -0.09
     OCI
    -0.09
    POSITIVE LOGITS
     Jug
    0.24
     Archie
    0.24
     Veronica
    0.15
     River
    0.14
     Slug
    0.13
     Betty
    0.13
     Trout
    0.13
     jug
    0.13
     Claud
    0.13
     Mädchen
    0.13
    Activations Density 0.095%

    No Known Activations