© 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. 5093
    Prev
    Next
    INDEX
    Explanations

    "you" or "us" followed by punctuation

    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
    psc
    -0.09
    -radius
    -0.09
     properly
    -0.09
    ?";↵
    -0.09
     prospect
    -0.09
    -_
    -0.09
    _nth
    -0.09
    PG
    -0.09
     um
    -0.09
     ith
    -0.08
    POSITIVE LOGITS
     now
    0.12
    NOW
    0.11
     remember
    0.10
     NOW
    0.10
    linger
    0.09
     Junction
    0.09
     WHETHER
    0.09
    undry
    0.09
    ãģĿãģĹãģ¦
    0.09
    uur
    0.09
    Activations Density 0.040%

    No Known Activations