© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27603
    Prev
    Next
    INDEX
    Explanations

    edition or version

    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
     plainly
    -0.10
     outright
    -0.09
     larg
    -0.08
    иÑħ
    -0.08
     dar
    -0.08
     jab
    -0.08
     Warn
    -0.08
    ื
    -0.08
     vit
    -0.08
     mater
    -0.08
    POSITIVE LOGITS
     edition
    0.61
     Edition
    0.59
    edition
    0.42
    Edition
    0.41
     editions
    0.41
     version
    0.34
    çīĪ
    0.31
     Version
    0.29
    Version
    0.24
    ç¯
    0.24
    Activations Density 0.535%

    No Known Activations