© 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. 112482
    Prev
    Next
    INDEX
    Explanations

    license/notice, attachments, header

    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
     unexpectedly
    -0.08
    icles
    -0.08
     focused
    -0.08
    colon
    -0.08
    focused
    -0.08
     EAR
    -0.08
     dag
    -0.08
    il
    -0.07
    ITO
    -0.07
     Revel
    -0.07
    POSITIVE LOGITS
     intact
    0.20
     attached
    0.14
     Attached
    0.12
     Verm
    0.12
    gard
    0.12
     accompanying
    0.12
     preserved
    0.11
     attachments
    0.11
     accompanies
    0.11
     Attach
    0.11
    Activations Density 0.073%

    No Known Activations