© 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. 89241
    Prev
    Next
    INDEX
    Explanations

    an article preceding a noun

    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
     teammate
    -0.16
     fellow
    -0.13
     partner
    -0.13
     opponent
    -0.12
     companion
    -0.12
    partner
    -0.12
     teammates
    -0.11
    Partner
    -0.11
     colleague
    -0.11
     cousin
    -0.11
    POSITIVE LOGITS
     young
    0.22
     wid
    0.18
     ordinary
    0.17
    young
    0.16
     bored
    0.15
     ambitious
    0.14
     lonely
    0.14
     aspiring
    0.14
     college
    0.14
     Ordinary
    0.13
    Activations Density 0.164%

    No Known Activations