© 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. 91087
    Prev
    Next
    INDEX
    Explanations

    starts with `if` then `Intent` or `is` then `some`

    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
     mist
    -0.09
     disguised
    -0.08
     synonyms
    -0.08
     appar
    -0.08
    omas
    -0.07
     rhyth
    -0.07
    Fi
    -0.07
     Finch
    -0.07
     solemn
    -0.07
     Gent
    -0.07
    POSITIVE LOGITS
    utz
    0.11
     spi
    0.10
    inel
    0.10
    anst
    0.10
    965
    0.10
     Nel
    0.10
     Bam
    0.10
    swith
    0.10
     MLB
    0.10
    vida
    0.10
    Activations Density 0.221%

    No Known Activations