© 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. 16336
    Prev
    Next
    INDEX
    Explanations

    numbers after symbols

    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
    inky
    -0.09
     deco
    -0.09
     verr
    -0.08
    ibold
    -0.08
     onStart
    -0.08
     squeezing
    -0.08
     organised
    -0.08
     bait
    -0.08
     Herr
    -0.08
     Schwartz
    -0.08
    POSITIVE LOGITS
    /API
    0.11
    Ĝ
    0.11
    75
    0.10
     rouge
    0.10
    agas
    0.10
    60
    0.10
    adesh
    0.09
    70
    0.09
    65
    0.09
     mouseY
    0.09
    Activations Density 0.760%

    No Known Activations