© 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. 113612
    Prev
    Next
    INDEX
    Explanations

    years or earlier

    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
    AMS
    -0.11
     Minute
    -0.10
    boro
    -0.10
     minute
    -0.10
    itar
    -0.10
    ieri
    -0.10
    yr
    -0.10
     ALWAYS
    -0.09
    _assert
    -0.09
    ines
    -0.09
    POSITIVE LOGITS
     unlucky
    0.10
    /free
    0.09
     nightly
    0.09
     meas
    0.08
     quotid
    0.08
     lucky
    0.08
    outu
    0.08
     calend
    0.07
     Gingrich
    0.07
    arkin
    0.07
    Activations Density 0.264%

    No Known Activations