© 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. 14170
    Prev
    Next
    INDEX
    Explanations

    than fact or ever

    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
     Neg
    -0.12
     UD
    -0.11
    amar
    -0.10
     CLK
    -0.10
    _dy
    -0.10
     accordingly
    -0.10
    881
    -0.09
     nowrap
    -0.09
     Cousins
    -0.09
    otte
    -0.09
    POSITIVE LOGITS
     breath
    0.09
     else
    0.09
     Hover
    0.09
    elyn
    0.08
    rea
    0.08
    izio
    0.08
     Else
    0.08
    asion
    0.08
     BRE
    0.08
    ube
    0.08
    Activations Density 0.001%

    No Known Activations