© 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. 50130
    Prev
    Next
    INDEX
    Explanations

    many followed by a plural noun or quantifier

    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
     several
    -0.13
     plenty
    -0.12
     ones
    -0.12
     alot
    -0.11
     many
    -0.11
    ories
    -0.10
     Couple
    -0.10
    fy
    -0.10
     terminology
    -0.10
     imagery
    -0.10
    POSITIVE LOGITS
    /all
    0.14
     calories
    0.13
     ifs
    0.11
     hours
    0.11
    /no
    0.11
     darn
    0.11
     of
    0.10
     damn
    0.10
     cents
    0.09
     bytes
    0.09
    Activations Density 0.045%

    No Known Activations