© 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. 49193
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with negative numbers

    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
     sle
    -0.07
     prejud
    -0.07
     priv
    -0.07
     pinch
    -0.07
     jewel
    -0.07
     whit
    -0.07
     Kath
    -0.07
     âĵĺ
    -0.07
     globalization
    -0.07
     privat
    -0.06
    POSITIVE LOGITS
    ?↵↵↵↵
    0.11
    fuck
    0.11
     exce
    0.11
     fuck
    0.10
    .↵↵↵↵↵
    0.10
     '\\'
    0.10
     FUCK
    0.10
    ugu
    0.10
    Shock
    0.10
    asz
    0.10
    Activations Density 0.103%

    No Known Activations