© 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. 47927
    Prev
    Next
    INDEX
    Explanations

    source file

    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
     unh
    -0.09
     Saras
    -0.08
     RP
    -0.08
     inters
    -0.08
     Bryce
    -0.08
     Tah
    -0.08
    format
    -0.08
    è¾ĵ
    -0.08
     Sahara
    -0.08
    Misc
    -0.07
    POSITIVE LOGITS
     briefly
    0.10
     Carlo
    0.10
     Govern
    0.10
     unders
    0.10
    cron
    0.10
     Lorenzo
    0.10
     Fou
    0.10
     Rath
    0.10
     overrun
    0.10
    ewolf
    0.10
    Activations Density 0.001%

    No Known Activations