© 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. 49933
    Prev
    Next
    INDEX
    Explanations

    sul- prefixes

    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
    oria
    -0.12
    esen
    -0.12
    ores
    -0.11
     upsetting
    -0.11
     negate
    -0.10
     pissed
    -0.10
     outdoors
    -0.10
    ¾
    -0.10
    lad
    -0.10
    nal
    -0.10
    POSITIVE LOGITS
     Bee
    0.08
    illi
    0.08
     Wins
    0.07
     beck
    0.07
     wins
    0.07
     HS
    0.07
    (dt
    0.07
     Roh
    0.07
    Ø·
    0.06
     Battles
    0.06
    Activations Density 0.002%

    No Known Activations