© 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. 15586
    Prev
    Next
    INDEX
    Explanations

    describes qualities

    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
     stray
    -0.09
    olk
    -0.09
    burgh
    -0.09
    abet
    -0.08
    och
    -0.08
    loh
    -0.08
    egl
    -0.08
    716
    -0.08
    oli
    -0.08
     Bened
    -0.08
    POSITIVE LOGITS
     calm
    0.17
     sleek
    0.17
     warm
    0.16
     loud
    0.15
     clean
    0.15
     concise
    0.15
     terse
    0.15
     witty
    0.15
     compact
    0.15
     neither
    0.15
    Activations Density 0.754%

    No Known Activations