© 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. 117091
    Prev
    Next
    INDEX
    Explanations

    appeal from the county court

    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
     Wand
    -0.09
     McCarthy
    -0.09
    irit
    -0.09
    elog
    -0.09
    sing
    -0.08
    rias
    -0.08
     Ho
    -0.08
     anyway
    -0.08
     nightly
    -0.08
    Morning
    -0.08
    POSITIVE LOGITS
    MZ
    0.10
    rette
    0.10
     protr
    0.10
     fier
    0.10
     Frid
    0.09
    ÙĪر
    0.09
    utter
    0.09
    æij
    0.09
    igure
    0.09
     PART
    0.09
    Activations Density 0.002%

    No Known Activations