© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49926
    Prev
    Next
    INDEX
    Explanations

    only before quantities or timeframes

    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
     insufficient
    -0.10
    iks
    -0.09
    igu
    -0.09
     Ath
    -0.09
    BO
    -0.08
     Klo
    -0.08
    sex
    -0.08
    ikan
    -0.08
    nen
    -0.08
    032
    -0.08
    POSITIVE LOGITS
     moderately
    0.16
     mildly
    0.14
     lightly
    0.12
     partially
    0.12
     slightly
    0.12
     Moder
    0.12
     Moderate
    0.12
     partly
    0.12
     modest
    0.11
     moderate
    0.11
    Activations Density 0.071%

    No Known Activations