© 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. 91223
    Prev
    Next
    INDEX
    Explanations

    from 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
     ladder
    -0.10
    koa
    -0.10
    895
    -0.10
    ulg
    -0.10
     Robbins
    -0.10
     sina
    -0.10
     artic
    -0.10
     impulse
    -0.10
    ideo
    -0.10
     articulate
    -0.10
    POSITIVE LOGITS
    onto
    0.09
     vents
    0.08
     beneath
    0.08
     Brushes
    0.08
    angep
    0.08
     diagon
    0.08
     unseen
    0.08
     Beaut
    0.08
     Merry
    0.08
     onto
    0.08
    Activations Density 0.044%

    No Known Activations