© 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. 14687
    Prev
    Next
    INDEX
    Explanations

    describing qualities or attributes

    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
     grat
    -0.13
     crud
    -0.11
     Enjoy
    -0.11
     prey
    -0.10
     embarrass
    -0.10
     fodder
    -0.09
     glor
    -0.09
     opportunity
    -0.09
     embarrassment
    -0.09
    Enjoy
    -0.09
    POSITIVE LOGITS
     skills
    0.24
     expertise
    0.22
     abilities
    0.20
     charisma
    0.18
     antics
    0.18
    skills
    0.18
     Skills
    0.18
     talents
    0.18
     actions
    0.18
     capabilities
    0.18
    Activations Density 0.003%

    No Known Activations