© 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. 115378
    Prev
    Next
    INDEX
    Explanations

    experience and skills

    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
     recipro
    -0.09
     Mutual
    -0.09
    orch
    -0.09
     Archae
    -0.09
    /shared
    -0.08
     DIM
    -0.08
    olu
    -0.08
     Gov
    -0.08
    uner
    -0.08
     mutual
    -0.08
    POSITIVE LOGITS
     multit
    0.23
     interpersonal
    0.21
    Ability
    0.17
     Ability
    0.17
     ability
    0.16
     adapt
    0.16
     customer
    0.16
     calm
    0.15
     interacting
    0.15
     communication
    0.15
    Activations Density 0.142%

    No Known Activations