© 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. 92149
    Prev
    Next
    INDEX
    Explanations

    acting as support or guide

    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
     newcomers
    -0.12
     billionaires
    -0.12
     smokers
    -0.11
     billionaire
    -0.11
     incumb
    -0.11
    eken
    -0.10
     smoker
    -0.10
     Veteran
    -0.09
     rookies
    -0.09
     teenager
    -0.09
    POSITIVE LOGITS
     facilit
    0.28
     catalyst
    0.24
     guar
    0.23
     guardian
    0.23
     mediator
    0.22
     arbitr
    0.21
     caret
    0.21
     advocate
    0.20
     protector
    0.20
     overse
    0.19
    Activations Density 0.517%

    No Known Activations