© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46225
    Prev
    Next
    INDEX
    Explanations

    dates followed by years

    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
    Negative Logits
    er
    -0.12
    erd
    -0.10
    alam
    -0.09
    erde
    -0.09
    arios
    -0.09
    alis
    -0.09
    eper
    -0.09
    oft
    -0.09
    à¯įà®
    -0.09
    eus
    -0.09
    POSITIVE LOGITS
    s
    0.18
    uelve
    0.13
    antage
    0.12
    olution
    0.12
    sky
    0.12
    ices
    0.11
    /null
    0.11
    olved
    0.11
    olve
    0.11
    engers
    0.11
    Activations Density 0.183%

    No Known Activations