© 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. 5366
    Prev
    Next
    INDEX
    Explanations

    Rajasthani or names with 'aj' suffix

    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
    /by
    -0.11
    eus
    -0.10
    alls
    -0.10
    stand
    -0.10
    ARB
    -0.10
    angelo
    -0.10
    andum
    -0.09
    orr
    -0.09
    o
    -0.09
     PRI
    -0.09
    POSITIVE LOGITS
    enko
    0.12
    ews
    0.11
    urved
    0.10
    ÃŃc
    0.10
    ew
    0.10
     Gast
    0.09
    kowski
    0.09
     Fuller
    0.09
    dzi
    0.09
    ean
    0.09
    Activations Density 0.032%

    No Known Activations