© 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. 47669
    Prev
    Next
    INDEX
    Explanations

    quantifier or number followed by related word

    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
     Stanton
    -0.08
     irr
    -0.08
    kes
    -0.07
     splitted
    -0.07
     sleeping
    -0.07
     inflated
    -0.07
     inherently
    -0.07
     neighbouring
    -0.07
     hurting
    -0.07
     foundations
    -0.07
    POSITIVE LOGITS
     double
    0.11
     relinqu
    0.11
     additional
    0.10
     Fay
    0.10
    amon
    0.10
     rearr
    0.10
     Caj
    0.09
     backward
    0.09
    beck
    0.09
     triple
    0.09
    Activations Density 0.050%

    No Known Activations