© 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. 49697
    Prev
    Next
    INDEX
    Explanations

    ag and agg prefixes

    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
    outh
    -0.09
    gers
    -0.08
    elman
    -0.08
    å¼ı
    -0.08
     Lager
    -0.08
    ousse
    -0.07
    arem
    -0.07
    hausen
    -0.07
    heimer
    -0.07
    orge
    -0.07
    POSITIVE LOGITS
    /ag
    0.19
    (ag
    0.18
     ag
    0.17
     aggrav
    0.17
    -ag
    0.15
     Ag
    0.15
     aggravated
    0.14
     agg
    0.13
    Uvs
    0.13
    .Ag
    0.13
    Activations Density 0.085%

    No Known Activations