© 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. 116891
    Prev
    Next
    INDEX
    Explanations

    links or separators

    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
    inden
    -0.10
     Gwen
    -0.10
     Knox
    -0.10
    otre
    -0.10
    iji
    -0.10
    kir
    -0.10
    uttle
    -0.10
    ereo
    -0.09
     Dillon
    -0.09
    ewan
    -0.09
    POSITIVE LOGITS
    ï¸ı
    0.18
     Mane
    0.11
    à¯į
    0.10
    ters
    0.10
    uto
    0.10
     Yam
    0.10
    .jsp
    0.09
    itet
    0.09
     emoji
    0.09
     âľĵ
    0.09
    Activations Density 0.035%

    No Known Activations