© 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. 117156
    Prev
    Next
    INDEX
    Explanations

    date and time stamps

    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
     paren
    -0.08
     notions
    -0.08
     subordinate
    -0.07
     drafts
    -0.07
    KEEP
    -0.07
     dense
    -0.07
     trio
    -0.07
     ECM
    -0.07
    pas
    -0.07
    Pinterest
    -0.07
    POSITIVE LOGITS
     tact
    0.11
     prer
    0.10
    iras
    0.10
     fro
    0.10
     '),
    0.10
     outward
    0.10
     jew
    0.09
    tester
    0.09
     immac
    0.09
     mush
    0.09
    Activations Density 1.135%

    No Known Activations