© 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. 116651
    Prev
    Next
    INDEX
    Explanations

    best plan

    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
     apparently
    -0.11
     supposedly
    -0.10
     allegedly
    -0.10
     presumably
    -0.09
     chim
    -0.09
     Apparently
    -0.08
    Apparently
    -0.08
     besie
    -0.07
     ÃĤ
    -0.07
     carn
    -0.07
    POSITIVE LOGITS
     Editors
    0.20
     overall
    0.18
     Overall
    0.16
    Overall
    0.16
     Runner
    0.15
     Editor
    0.14
     runner
    0.14
    Runner
    0.14
    (op
    0.13
    Editor
    0.13
    Activations Density 0.137%

    No Known Activations