© 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. 31029
    Prev
    Next
    INDEX
    Explanations

    aff or af prefix expansion

    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
    ays
    -0.07
    iers
    -0.07
     finish
    -0.07
     perish
    -0.07
     Roose
    -0.07
     gross
    -0.07
     Finish
    -0.07
     plot
    -0.06
     Lindsey
    -0.06
    Tau
    -0.06
    POSITIVE LOGITS
     Aff
    0.16
     affection
    0.15
     affinity
    0.15
    -aff
    0.14
    Aff
    0.14
     AFF
    0.14
    aff
    0.13
     affine
    0.13
     Affairs
    0.13
     aff
    0.13
    Activations Density 0.019%

    No Known Activations