© 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. 25396
    Prev
    Next
    INDEX
    Explanations

    balancing work, life, school

    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
     Comfort
    -0.13
     terrified
    -0.12
     safest
    -0.12
     nerv
    -0.12
     embarrassing
    -0.11
    moid
    -0.11
    Comfort
    -0.11
     anatom
    -0.11
    confidence
    -0.11
    Safe
    -0.11
    POSITIVE LOGITS
     priorit
    0.39
     priorities
    0.35
     prioritize
    0.32
     priority
    0.30
     sacrifices
    0.29
     sacrifice
    0.28
     Priority
    0.27
     sacrificing
    0.26
     scheduling
    0.26
     Sacr
    0.25
    Activations Density 0.328%

    No Known Activations