© 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. 50935
    Prev
    Next
    INDEX
    Explanations

    medulloblastomas

    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
    irse
    -0.11
     maturity
    -0.10
    ért
    -0.10
     METH
    -0.10
    umm
    -0.10
    andr
    -0.10
    NR
    -0.10
    AME
    -0.10
    Â
    -0.10
    _managed
    -0.10
    POSITIVE LOGITS
     pals
    0.08
     Spear
    0.08
     Gibson
    0.07
     Camb
    0.07
     Carlton
    0.07
     shar
    0.07
     hull
    0.07
    orra
    0.07
     rally
    0.07
    inx
    0.07
    Activations Density 0.001%

    No Known Activations