© 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. 28118
    Prev
    Next
    INDEX
    Explanations

    Carmel or Carmine

    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
    ager
    -0.10
    amb
    -0.10
    AGER
    -0.10
    ary
    -0.10
    /pre
    -0.10
    AMB
    -0.09
    inke
    -0.09
    osta
    -0.09
     reim
    -0.09
    erte
    -0.09
    POSITIVE LOGITS
    elo
    0.11
    eli
    0.11
    elite
    0.10
    etat
    0.10
    inez
    0.10
     Candy
    0.10
    ichael
    0.10
    ody
    0.09
    argo
    0.09
    ela
    0.09
    Activations Density 0.003%

    No Known Activations