© 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. 48203
    Prev
    Next
    INDEX
    Explanations

    valuable time and resources

    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
    lop
    -0.11
     Pearce
    -0.10
    097
    -0.09
     Recycling
    -0.09
     recycling
    -0.09
     forfe
    -0.08
     maximizing
    -0.08
    Brit
    -0.08
    chos
    -0.08
     occupations
    -0.08
    POSITIVE LOGITS
     energy
    0.26
     resources
    0.26
     money
    0.20
     time
    0.19
     Resources
    0.18
     funds
    0.18
    èµĦæºIJ
    0.18
     Energy
    0.18
    resources
    0.17
     energies
    0.16
    Activations Density 0.129%

    No Known Activations