© 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. 3710
    Prev
    Next
    INDEX
    Explanations

    24 hours

    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
     alternatively
    -0.10
    seite
    -0.08
    enu
    -0.08
    pei
    -0.08
     disadvantage
    -0.08
    edia
    -0.08
    cia
    -0.08
     coinc
    -0.08
     pencil
    -0.08
    compression
    -0.08
    POSITIVE LOGITS
     Hour
    0.13
    hour
    0.12
     hour
    0.12
    Hour
    0.12
    -hour
    0.12
     rond
    0.11
     anytime
    0.11
     HOUR
    0.10
    /all
    0.10
    urnal
    0.10
    Activations Density 0.013%

    No Known Activations