© 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. 33940
    Prev
    Next
    INDEX
    Explanations

    returning to the

    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
     slightest
    -0.14
     occasional
    -0.10
    ither
    -0.10
    ici
    -0.10
     advance
    -0.10
    ullah
    -0.10
     closely
    -0.10
     bonus
    -0.09
     pinch
    -0.09
     quickest
    -0.09
    POSITIVE LOGITS
     fray
    0.14
     basics
    0.13
     original
    0.12
     comforts
    0.12
     reverted
    0.11
     interrupted
    0.11
     hustle
    0.10
     normal
    0.10
     whence
    0.10
     Earlier
    0.10
    Activations Density 0.035%

    No Known Activations