© 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. 46955
    Prev
    Next
    INDEX
    Explanations

    names ending in i, ori, or y

    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
    ooth
    -0.10
    ums
    -0.09
    frame
    -0.09
    à¹Į
    -0.08
    ize
    -0.08
     ad
    -0.08
    eron
    -0.08
    ister
    -0.08
     vot
    -0.08
     skew
    -0.08
    POSITIVE LOGITS
    ente
    0.11
    hiro
    0.11
    ansson
    0.10
    ema
    0.10
     highly
    0.10
    ander
    0.10
    elta
    0.09
    annt
    0.09
     Advance
    0.09
     policing
    0.09
    Activations Density 0.015%

    No Known Activations