© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114812
    Prev
    Next
    INDEX
    Explanations

    billionaire philanthropist

    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
     camar
    -0.12
     teacher
    -0.10
    @student
    -0.10
     barber
    -0.10
     sergeant
    -0.10
     beads
    -0.09
     cowork
    -0.09
     Bowling
    -0.09
    /wait
    -0.09
     teachers
    -0.09
    POSITIVE LOGITS
     billionaire
    0.44
     billionaires
    0.40
     wealthy
    0.39
     wealth
    0.39
     Wealth
    0.36
     millionaire
    0.34
     philanth
    0.33
     wealthiest
    0.33
    wealth
    0.32
     Billion
    0.30
    Activations Density 0.398%

    No Known Activations