© 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. 88649
    Prev
    Next
    INDEX
    Explanations

    after a certain time

    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
    qd
    -0.10
    rey
    -0.10
    inx
    -0.09
     pud
    -0.09
    Exceptions
    -0.09
    RTC
    -0.09
    iya
    -0.09
    ixin
    -0.09
    arme
    -0.09
    illo
    -0.09
    POSITIVE LOGITS
     awhile
    0.34
     eventually
    0.28
     Eventually
    0.25
    Eventually
    0.25
     eventual
    0.20
     sometime
    0.19
     finally
    0.15
     sooner
    0.14
     ultimately
    0.14
     someday
    0.13
    Activations Density 0.056%

    No Known Activations