© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115257
    Prev
    Next
    INDEX
    Explanations

    solitude and quiet reflection

    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
     enthusiastically
    -0.09
    ennon
    -0.09
    aben
    -0.09
     curiosity
    -0.09
     Shib
    -0.08
     pudd
    -0.08
    meter
    -0.08
    /games
    -0.08
     veto
    -0.08
     deem
    -0.08
    POSITIVE LOGITS
     solitude
    0.26
     thoughts
    0.26
     contempl
    0.24
     intros
    0.23
     Thoughts
    0.22
     reflection
    0.21
     quiet
    0.20
    æĢĿ
    0.20
     meditation
    0.19
     reflective
    0.19
    Activations Density 0.094%

    No Known Activations