© 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. 5240
    Prev
    Next
    INDEX
    Explanations

    passed away

    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
     Gew
    -0.08
     Wheels
    -0.08
     Sen
    -0.08
     Counts
    -0.08
    RAW
    -0.08
    Sen
    -0.08
     sorted
    -0.08
    ettle
    -0.08
    tractor
    -0.08
     body
    -0.07
    POSITIVE LOGITS
    /pass
    0.12
     unconscious
    0.11
     miser
    0.11
    Limits
    0.11
     muster
    0.11
     dau
    0.11
     Stage
    0.10
    /de
    0.10
    ively
    0.10
     limits
    0.10
    Activations Density 0.006%

    No Known Activations