© 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. 25579
    Prev
    Next
    INDEX
    Explanations

    suit or satisfy

    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
    ieri
    -0.10
    emento
    -0.10
     Hass
    -0.09
    enis
    -0.09
     Minh
    -0.09
     autop
    -0.09
    Liked
    -0.09
     shar
    -0.09
    ool
    -0.08
    oyer
    -0.08
    POSITIVE LOGITS
     cater
    0.36
     catering
    0.34
     Cater
    0.30
     accommodate
    0.21
     satisfy
    0.20
     accommodating
    0.20
     accommod
    0.19
     suit
    0.18
     satisfies
    0.18
     cat
    0.17
    Activations Density 0.074%

    No Known Activations