© 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. 32095
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    erval
    -0.11
    LN
    -0.10
     Contest
    -0.10
    plib
    -0.10
     contexts
    -0.10
    noch
    -0.10
     Thrones
    -0.10
    scratch
    -0.09
    .props
    -0.09
     kü
    -0.09
    POSITIVE LOGITS
     hourly
    0.11
     fel
    0.09
     lump
    0.08
     Wilde
    0.08
     Bea
    0.08
     awaken
    0.08
     woke
    0.08
    rello
    0.08
    weekly
    0.08
     lure
    0.08
    Activations Density 0.069%

    No Known Activations