© 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. 88953
    Prev
    Next
    INDEX
    Explanations

    approaching events

    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
    esk
    -0.09
     Moved
    -0.08
     Heard
    -0.08
    udas
    -0.08
    counts
    -0.08
     Griffin
    -0.08
     cus
    -0.08
    ahan
    -0.08
     smashed
    -0.08
    iet
    -0.07
    POSITIVE LOGITS
     imminent
    0.22
     ens
    0.21
     arrives
    0.20
     arrived
    0.20
     arrive
    0.20
     onset
    0.19
     elusive
    0.19
     Comes
    0.18
     creeping
    0.18
     looming
    0.18
    Activations Density 0.073%

    No Known Activations