© 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. 3782
    Prev
    Next
    INDEX
    Explanations

    event/date 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
     immediate
    -0.17
     immediately
    -0.14
     Immediate
    -0.14
     immedi
    -0.12
     instantly
    -0.12
    Immediate
    -0.12
     imminent
    -0.11
     whilst
    -0.11
     Immediately
    -0.10
    ipe
    -0.10
    POSITIVE LOGITS
     RSVP
    0.15
     Thursday
    0.14
     arrives
    0.13
     noon
    0.13
     arrive
    0.13
     attendance
    0.12
     arriving
    0.12
    wear
    0.12
     meeting
    0.12
     Bring
    0.12
    Activations Density 0.083%

    No Known Activations