© 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. 3503
    Prev
    Next
    INDEX
    Explanations

    too

    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
    ration
    -0.12
     Ker
    -0.11
     Buck
    -0.11
     Medi
    -0.10
    .hex
    -0.10
    izi
    -0.10
    hen
    -0.10
     Blanco
    -0.10
     Oval
    -0.10
    _house
    -0.10
    POSITIVE LOGITS
    o
    0.11
     plung
    0.09
     albeit
    0.09
    tl
    0.08
    agar
    0.08
    Oi
    0.08
     fir
    0.08
    dl
    0.08
     padd
    0.07
    -sama
    0.07
    Activations Density 0.037%

    No Known Activations