© 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. 27923
    Prev
    Next
    INDEX
    Explanations

    business partners, romantic partners, lovers

    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
     bearer
    -0.12
     Murphy
    -0.11
    hood
    -0.11
     professionally
    -0.11
     datings
    -0.10
     unlucky
    -0.10
     bonds
    -0.10
     freak
    -0.10
     DIR
    -0.10
    ationship
    -0.10
    POSITIVE LOGITS
     Trades
    0.08
     Widgets
    0.08
     Ung
    0.08
     Vaults
    0.07
    odo
    0.07
     Trails
    0.07
     aba
    0.07
    aber
    0.07
    ensi
    0.07
    è¯ķ
    0.07
    Activations Density 0.022%

    No Known Activations