© 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. 29702
    Prev
    Next
    INDEX
    Explanations

    demographics and groups

    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
    osi
    -0.08
    /up
    -0.08
     costume
    -0.07
    wand
    -0.07
     invitations
    -0.07
    ullo
    -0.07
    esser
    -0.06
     Davies
    -0.06
     deliveries
    -0.06
    yor
    -0.06
    POSITIVE LOGITS
     behaving
    0.21
     doing
    0.15
     everywhere
    0.14
     deserve
    0.14
     Doing
    0.14
     unite
    0.13
     UNITED
    0.13
     reacting
    0.13
     ROCK
    0.13
     united
    0.12
    Activations Density 0.110%

    No Known Activations