© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    if i'd be interested

    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
     Kah
    -0.09
    /fr
    -0.09
     Kil
    -0.09
    ratings
    -0.09
    oppers
    -0.09
     habit
    -0.09
     Dul
    -0.09
     contradictions
    -0.09
    ichen
    -0.09
    ADM
    -0.09
    POSITIVE LOGITS
     interested
    0.65
     interest
    0.63
     Interested
    0.56
     Interest
    0.55
    interested
    0.50
    interest
    0.47
    Interested
    0.46
    Interest
    0.46
    -interest
    0.45
     interests
    0.41
    Activations Density 0.206%

    No Known Activations