© 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. 13980
    Prev
    Next
    INDEX
    Explanations

    gustavo, guttatus, Gurtina

    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
     Sec
    -0.11
    orr
    -0.09
     unstoppable
    -0.09
    edor
    -0.09
    eki
    -0.09
    _Se
    -0.09
     reciprocal
    -0.09
     spare
    -0.09
     lightly
    -0.09
    oke
    -0.09
    POSITIVE LOGITS
    ierrez
    0.14
    ormsg
    0.11
     gut
    0.11
     Gut
    0.10
     Burl
    0.09
    brands
    0.09
    licht
    0.09
    arı
    0.09
    ible
    0.09
    iver
    0.09
    Activations Density 0.043%

    No Known Activations