© 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. 46025
    Prev
    Next
    INDEX
    Explanations

    flo, flop, flip, float, lop

    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
     Temple
    -0.09
     needless
    -0.09
    ores
    -0.09
     jam
    -0.09
    ems
    -0.09
     Jam
    -0.09
    .RELATED
    -0.09
    er
    -0.09
     gou
    -0.08
    Jam
    -0.08
    POSITIVE LOGITS
     onto
    0.16
     flop
    0.13
     floppy
    0.13
     flo
    0.11
    flip
    0.11
    vang
    0.11
     favicon
    0.10
    fish
    0.10
     unto
    0.10
    -thumb
    0.10
    Activations Density 0.001%

    No Known Activations