© 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. 88796
    Prev
    Next
    INDEX
    Explanations

    gives opportunity or ability

    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
    apur
    -0.10
    adt
    -0.10
     Hos
    -0.09
    ном
    -0.09
     stale
    -0.09
     arrang
    -0.09
     ARR
    -0.09
    illow
    -0.09
     Franken
    -0.09
    PW
    -0.09
    POSITIVE LOGITS
     opportunity
    0.18
     chance
    0.17
     footh
    0.13
     ability
    0.13
     opportunities
    0.11
     flexibility
    0.10
     freedom
    0.10
     access
    0.10
     option
    0.09
     le
    0.09
    Activations Density 0.089%

    No Known Activations