© 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. 46899
    Prev
    Next
    INDEX
    Explanations

    about what happened

    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
    Scope
    -0.10
    esch
    -0.09
     mourn
    -0.09
    Vac
    -0.09
     Features
    -0.09
    acity
    -0.09
    (Expected
    -0.09
    ons
    -0.09
     Dimensions
    -0.09
    hn
    -0.09
    POSITIVE LOGITS
     yesterday
    0.21
     recent
    0.18
     what
    0.17
     incident
    0.17
     events
    0.15
    incident
    0.15
     Incident
    0.15
     Saturday
    0.14
     Monday
    0.13
    what
    0.13
    Activations Density 0.125%

    No Known Activations