© 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. 6852
    Prev
    Next
    INDEX
    Explanations

    names appearing in text

    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
     van
    -0.10
    stroy
    -0.10
     Dorm
    -0.10
    iswa
    -0.10
    alem
    -0.10
     creep
    -0.10
    ipay
    -0.09
    vana
    -0.09
     Mb
    -0.09
     irresist
    -0.09
    POSITIVE LOGITS
     atmos
    0.09
    bower
    0.09
    ledge
    0.09
    ley
    0.08
    anske
    0.08
    @class
    0.08
     [#
    0.08
    ugins
    0.08
    ison
    0.08
    zend
    0.08
    Activations Density 1.010%

    No Known Activations