© 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. 90750
    Prev
    Next
    INDEX
    Explanations

    getting or buying things

    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
     Huff
    -0.13
    -Cal
    -0.12
    jay
    -0.11
    ropp
    -0.11
    asha
    -0.11
     overs
    -0.11
    itals
    -0.11
    perl
    -0.10
    .less
    -0.10
    antas
    -0.10
    POSITIVE LOGITS
     seperate
    0.12
     separate
    0.11
     Separate
    0.09
     memberships
    0.08
     licences
    0.08
     cheaper
    0.08
    /download
    0.08
     membership
    0.08
     licenses
    0.08
     subscriptions
    0.08
    Activations Density 0.113%

    No Known Activations