© 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. 3430
    Prev
    Next
    INDEX
    Explanations

    positioning and timing

    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
     POSIX
    -0.11
     posit
    -0.10
     LinearLayoutManager
    -0.10
    edb
    -0.09
    iomanip
    -0.09
     Pose
    -0.09
     peaked
    -0.09
     positional
    -0.09
    cents
    -0.09
     Arn
    -0.09
    POSITIVE LOGITS
     durations
    0.10
    ï¿
    0.10
     FileAccess
    0.09
    setSize
    0.09
    è²
    0.09
     Damian
    0.09
    .ng
    0.09
    /Set
    0.09
     Timothy
    0.09
     soundtrack
    0.09
    Activations Density 0.207%

    No Known Activations