© 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. 50604
    Prev
    Next
    INDEX
    Explanations

    during a period or event

    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
     Lazar
    -0.09
     unused
    -0.09
     conc
    -0.09
    RD
    -0.08
     attachment
    -0.08
     effort
    -0.08
    icha
    -0.08
     holding
    -0.08
     kla
    -0.08
    Cascade
    -0.07
    POSITIVE LOGITS
     transitions
    0.16
     periods
    0.16
     winters
    0.14
     transition
    0.13
     rehears
    0.13
     adolescence
    0.13
     phases
    0.13
     storms
    0.13
     bouts
    0.13
     puberty
    0.13
    Activations Density 0.068%

    No Known Activations