© 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. 30873
    Prev
    Next
    INDEX
    Explanations

    encoded characters or symbols

    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
     diversified
    -0.07
     Parsons
    -0.07
    angi
    -0.06
    mana
    -0.06
    rut
    -0.06
    midi
    -0.06
     Vert
    -0.06
    /he
    -0.06
     Maya
    -0.06
    å¾Ħ
    -0.06
    POSITIVE LOGITS
    ÂĢÂĻ
    0.15
    âĤ¬âĦ¢
    0.15
    EUR
    0.13
    /pages
    0.13
    Â
    0.12
    ÂŃ
    0.12
     aide
    0.12
    Formats
    0.11
    Æ
    0.11
    ¬
    0.11
    Activations Density 0.082%

    No Known Activations