© 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. 88550
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by a connector

    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
    anon
    -0.11
     DC
    -0.09
     Hed
    -0.09
    oro
    -0.09
     Gib
    -0.09
     Brace
    -0.09
     Hor
    -0.09
    orr
    -0.09
    urch
    -0.09
     Cunningham
    -0.09
    POSITIVE LOGITS
     sar
    0.10
    -inf
    0.10
     SAR
    0.10
    inf
    0.10
     Sar
    0.09
     Douglas
    0.09
     STAR
    0.09
     Pond
    0.09
     Thatcher
    0.09
    ifax
    0.09
    Activations Density 0.044%

    No Known Activations