© 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. 13985
    Prev
    Next
    INDEX
    Explanations

    headed out or for

    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
    iese
    -0.12
    folio
    -0.11
     Cres
    -0.11
    sending
    -0.11
    jej
    -0.10
    aston
    -0.10
    overs
    -0.10
     Mane
    -0.10
    ICS
    -0.10
    jang
    -0.10
    POSITIVE LOGITS
     toward
    0.18
     towards
    0.18
     upstairs
    0.13
     back
    0.12
     home
    0.12
     downstairs
    0.12
     Towards
    0.11
     down
    0.11
     straight
    0.10
    Towards
    0.10
    Activations Density 0.010%

    No Known Activations