© 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. 15503
    Prev
    Next
    INDEX
    Explanations

    product description

    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
    daf
    -0.11
    еÑĪ
    -0.09
     RandomForest
    -0.09
     entrusted
    -0.09
     flaming
    -0.09
     mots
    -0.09
     bajo
    -0.09
    inta
    -0.09
    ecd
    -0.08
    kowski
    -0.08
    POSITIVE LOGITS
    coop
    0.10
     conson
    0.09
     conc
    0.09
     HG
    0.09
     Zimmer
    0.09
     ISC
    0.09
     Perr
    0.09
     Deploy
    0.08
     Gos
    0.08
     Bren
    0.08
    Activations Density 0.001%

    No Known Activations