© 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. 4223
    Prev
    Next
    INDEX
    Explanations

    date finder, single ads

    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
     Shack
    -0.09
     Conce
    -0.08
     extravagant
    -0.08
    UTF
    -0.08
     Rangers
    -0.08
    isclosed
    -0.08
     upfront
    -0.08
     Wa
    -0.08
    ember
    -0.07
    esses
    -0.07
    POSITIVE LOGITS
    /libs
    0.11
    chia
    0.10
     IDX
    0.10
    esi
    0.10
     ogl
    0.10
     NOTICE
    0.10
    flate
    0.10
     misd
    0.09
     asc
    0.09
    -max
    0.09
    Activations Density 0.003%

    No Known Activations