© 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. 49954
    Prev
    Next
    INDEX
    Explanations

    friendship and trust

    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
     poorly
    -0.09
     hastily
    -0.08
    ango
    -0.08
     arbitrarily
    -0.08
     wo
    -0.08
     Stranger
    -0.07
     Wonderland
    -0.07
     Krank
    -0.07
    elin
    -0.07
     encountered
    -0.07
    POSITIVE LOGITS
     trust
    0.21
     trusts
    0.20
     intimate
    0.18
     trusted
    0.18
     intimacy
    0.18
    Trust
    0.17
    trust
    0.17
     Trust
    0.17
     secrets
    0.16
     Trusted
    0.16
    Activations Density 0.069%

    No Known Activations