© 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. 90867
    Prev
    Next
    INDEX
    Explanations

    names like Lili, Lalley, Luis

    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
    eer
    -0.13
    aire
    -0.11
    eur
    -0.11
    eses
    -0.10
    tica
    -0.10
    aan
    -0.10
    /cop
    -0.10
    esses
    -0.10
    aat
    -0.09
    tte
    -0.09
    POSITIVE LOGITS
    ient
    0.11
    ith
    0.11
    ypad
    0.10
    acb
    0.10
    iana
    0.10
    cobra
    0.09
    iane
    0.09
    cron
    0.09
    ien
    0.09
    wort
    0.09
    Activations Density 0.005%

    No Known Activations