© 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. 7834
    Prev
    Next
    INDEX
    Explanations

    in peace or solitude

    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
    ADE
    -0.11
    tright
    -0.11
    XS
    -0.11
    vince
    -0.10
    _pan
    -0.10
     Peek
    -0.10
     CAUSED
    -0.10
     DBG
    -0.10
    invalidate
    -0.10
     motivo
    -0.10
    POSITIVE LOGITS
     silence
    0.35
     quietly
    0.30
     silently
    0.30
     silent
    0.26
     peacefully
    0.26
     Silence
    0.24
     peace
    0.23
     quiet
    0.21
     alone
    0.20
     solitude
    0.20
    Activations Density 0.088%

    No Known Activations