© 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. 46330
    Prev
    Next
    INDEX
    Explanations

    cosplay, cosplayers, cosmetics

    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
     illeg
    -0.10
     doub
    -0.10
    pais
    -0.09
     derby
    -0.09
    tie
    -0.09
    ator
    -0.09
     Greens
    -0.09
    nak
    -0.09
    ections
    -0.09
    eb
    -0.09
    POSITIVE LOGITS
     cosm
    0.15
     cos
    0.14
     Cos
    0.13
    mo
    0.12
    metics
    0.12
    cos
    0.11
    Cos
    0.11
     cosine
    0.11
     cosplay
    0.11
    play
    0.11
    Activations Density 0.011%

    No Known Activations