© 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. 47822
    Prev
    Next
    INDEX
    Explanations

    these or those followed by noun

    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
     admittedly
    -0.12
     decidedly
    -0.10
    onga
    -0.09
     quieter
    -0.08
     Fro
    -0.08
     vaguely
    -0.08
     olive
    -0.08
     fled
    -0.08
    /S
    -0.07
     fro
    -0.07
    POSITIVE LOGITS
     evid
    0.14
     stuff
    0.14
     bunch
    0.13
     equipments
    0.12
     mentioned
    0.12
    mentioned
    0.11
    stuff
    0.11
     termin
    0.11
    works
    0.11
     Stuff
    0.10
    Activations Density 0.109%

    No Known Activations