© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114244
    Prev
    Next
    INDEX
    Explanations

    as time progresses

    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
     hy
    -0.08
     companion
    -0.07
    ill
    -0.07
     Asi
    -0.07
    uzz
    -0.07
    ourn
    -0.07
    776
    -0.07
     explosion
    -0.06
    ür
    -0.06
     as
    -0.06
    POSITIVE LOGITS
     time
    0.20
    æŶéĹ´
    0.17
     progressed
    0.17
     weeks
    0.17
     months
    0.16
     progresses
    0.15
    =time
    0.15
     Months
    0.15
     days
    0.15
    æĻĤéĸĵ
    0.15
    Activations Density 0.058%

    No Known Activations