© 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. 7753
    Prev
    Next
    INDEX
    Explanations

    public appearances and roles

    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
    uala
    -0.10
    ulg
    -0.09
     Oc
    -0.09
     Previous
    -0.09
    ohl
    -0.09
     Pru
    -0.09
     Sold
    -0.09
     Wid
    -0.09
    üm
    -0.09
    erts
    -0.08
    POSITIVE LOGITS
     cameo
    0.14
     guest
    0.12
     pregnancy
    0.12
     commemor
    0.12
     featured
    0.12
     suing
    0.11
    appearance
    0.11
     hosting
    0.11
     collaboration
    0.11
     appearing
    0.11
    Activations Density 0.547%

    No Known Activations