© 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. 113034
    Prev
    Next
    INDEX
    Explanations

    state of being closed or disabled

    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
    agos
    -0.10
     GOT
    -0.09
     Voor
    -0.09
     impatient
    -0.09
    438
    -0.09
     lied
    -0.09
    rem
    -0.09
    chu
    -0.09
     kennen
    -0.08
    issen
    -0.08
    POSITIVE LOGITS
     intact
    0.17
     unchanged
    0.12
     still
    0.12
     turned
    0.11
     alive
    0.11
     Em
    0.11
     divided
    0.10
     tied
    0.10
     out
    0.10
     facing
    0.10
    Activations Density 0.057%

    No Known Activations