© 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. 14202
    Prev
    Next
    INDEX
    Explanations

    where you want or need

    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
     elsewhere
    -0.13
    /**↵↵
    -0.12
    648
    -0.12
    imu
    -0.12
     fondo
    -0.12
     fond
    -0.12
    OLT
    -0.12
     nowhere
    -0.11
    446
    -0.11
     everywhere
    -0.11
    POSITIVE LOGITS
     Positioned
    0.09
     positioned
    0.09
     positioning
    0.08
     position
    0.08
     Position
    0.08
     Located
    0.07
     placed
    0.07
     pf
    0.06
    Position
    0.06
    located
    0.06
    Activations Density 0.013%

    No Known Activations