© 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. 89484
    Prev
    Next
    INDEX
    Explanations

    etymology, origin, or source

    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
     Phil
    -0.11
     unofficial
    -0.10
    nev
    -0.10
    enia
    -0.10
     submenu
    -0.10
    elic
    -0.10
     recur
    -0.09
    ticks
    -0.09
    acha
    -0.09
     intuit
    -0.09
    POSITIVE LOGITS
     ultimately
    0.14
     Middle
    0.13
    ult
    0.12
     Ultimately
    0.11
     Old
    0.10
     att
    0.10
     earlier
    0.10
     ultimate
    0.09
     sooner
    0.09
     borrowed
    0.09
    Activations Density 0.286%

    No Known Activations