© 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. 29339
    Prev
    Next
    INDEX
    Explanations

    academic attendance

    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
     alma
    -0.11
    fec
    -0.10
    Junior
    -0.10
    agal
    -0.10
    ungs
    -0.10
     indemn
    -0.10
     unveiling
    -0.10
     fuss
    -0.09
     rej
    -0.09
    agger
    -0.09
    POSITIVE LOGITS
     attendance
    0.18
     Attendance
    0.17
     attends
    0.16
     attend
    0.16
     attentive
    0.16
     attent
    0.14
     attending
    0.14
    attendance
    0.14
     attended
    0.14
     Attend
    0.13
    Activations Density 0.116%

    No Known Activations