© 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. 25385
    Prev
    Next
    INDEX
    Explanations

    plural nouns ending in s or es

    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
    zon
    -0.09
     Trey
    -0.08
     centres
    -0.08
     undocumented
    -0.08
     rigid
    -0.08
     CAMERA
    -0.08
    Coder
    -0.08
     tandem
    -0.08
     removeFrom
    -0.08
     overlays
    -0.08
    POSITIVE LOGITS
     FAQ
    0.16
     Redux
    0.15
     overview
    0.15
     redux
    0.14
     revis
    0.14
     Expl
    0.14
     primer
    0.14
     Primer
    0.13
     roundup
    0.13
     FAQs
    0.13
    Activations Density 0.613%

    No Known Activations