© 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. 25286
    Prev
    Next
    INDEX
    Explanations

    JE followed by AN, FF, JU, ON, or followed by 's in jeep

    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
    wal
    -0.09
     scram
    -0.09
     practise
    -0.09
    eus
    -0.09
    deo
    -0.08
    ief
    -0.08
    oun
    -0.08
     retros
    -0.08
    endo
    -0.08
    xe
    -0.08
    POSITIVE LOGITS
    alous
    0.13
    ÅĽli
    0.13
     suis
    0.11
     lah
    0.11
    opard
    0.10
    ff
    0.10
     dow
    0.10
    brane
    0.10
    udi
    0.10
     jeep
    0.10
    Activations Density 0.012%

    No Known Activations