© 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. 27138
    Prev
    Next
    INDEX
    Explanations

    loved ones, partners relating

    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
     doomed
    -0.13
     friendly
    -0.12
     suffering
    -0.12
     sympathy
    -0.12
     su
    -0.11
     estr
    -0.11
     imperson
    -0.11
     selber
    -0.11
     suffer
    -0.11
     generic
    -0.11
    POSITIVE LOGITS
     stronghold
    0.12
     securely
    0.11
     femin
    0.10
     fiercely
    0.10
     intentional
    0.10
     priorit
    0.10
    adm
    0.10
     recip
    0.10
     unab
    0.10
     reassuring
    0.10
    Activations Density 0.025%

    No Known Activations