© 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. 88421
    Prev
    Next
    INDEX
    Explanations

    ability to / inability of

    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
     Pag
    -0.10
    ined
    -0.10
     sprayed
    -0.10
     Uzbek
    -0.10
    650
    -0.09
     deaf
    -0.09
    -Sah
    -0.09
     Montgomery
    -0.09
    adesh
    -0.09
     tempor
    -0.09
    POSITIVE LOGITS
    istros
    0.08
     baik
    0.08
     computers
    0.08
     satellites
    0.08
    appen
    0.08
    263
    0.08
    usk
    0.08
     bullets
    0.08
    ););↵
    0.08
    stants
    0.08
    Activations Density 1.403%

    No Known Activations