© 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. 16555
    Prev
    Next
    INDEX
    Explanations

    ultra resolution

    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
    Collapse
    -0.09
     obedience
    -0.08
     chores
    -0.08
     Yoshi
    -0.08
     Seymour
    -0.08
    Ord
    -0.08
    catch
    -0.08
     clic
    -0.08
     overlapping
    -0.08
    anova
    -0.08
    POSITIVE LOGITS
     resolution
    0.16
     ultra
    0.15
     Ultra
    0.14
     Resolution
    0.13
    Ultra
    0.12
    /U
    0.11
    -ready
    0.11
    -resolution
    0.11
     ultr
    0.10
    -cap
    0.10
    Activations Density 0.087%

    No Known Activations