© 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. 26506
    Prev
    Next
    INDEX
    Explanations

    focus and spotlight

    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
    827
    -0.10
     Sanity
    -0.10
     sanity
    -0.10
     opportun
    -0.10
    egin
    -0.10
    lag
    -0.09
    gy
    -0.09
    bern
    -0.09
     Orden
    -0.09
    emos
    -0.09
    POSITIVE LOGITS
     focus
    0.29
     spotlight
    0.28
     focusing
    0.25
     overshadow
    0.24
     focuses
    0.23
    focus
    0.23
     foreground
    0.22
     Focus
    0.22
    Focus
    0.22
     focal
    0.21
    Activations Density 0.106%

    No Known Activations