© 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. 115243
    Prev
    Next
    INDEX
    Explanations

    used after 'you' or 'i'

    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
     duo
    -0.12
     BOTH
    -0.12
    avorite
    -0.11
     admiration
    -0.11
     admire
    -0.11
     obsession
    -0.10
     Friendship
    -0.10
     hers
    -0.10
     obsess
    -0.10
     obsessed
    -0.10
    POSITIVE LOGITS
     surrounded
    0.23
     outnumber
    0.17
     amidst
    0.16
     distributing
    0.16
     distributed
    0.15
     circulated
    0.14
     singled
    0.14
     distribute
    0.14
     everyone
    0.14
     distributes
    0.14
    Activations Density 0.158%

    No Known Activations