© 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. 49205
    Prev
    Next
    INDEX
    Explanations

    go ahead and

    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
    æŀľ
    -0.09
    adas
    -0.09
    imat
    -0.09
     steering
    -0.09
    uren
    -0.09
     Rossi
    -0.09
     _↵
    -0.09
    SCAN
    -0.09
    aren
    -0.08
     Serial
    -0.08
    POSITIVE LOGITS
     upstairs
    0.10
     Concurrent
    0.09
     upstream
    0.09
     out
    0.09
     faithful
    0.09
     Ill
    0.08
     desper
    0.08
     lets
    0.08
    960
    0.08
    ellular
    0.08
    Activations Density 0.002%

    No Known Activations