© 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. 90668
    Prev
    Next
    INDEX
    Explanations

    difficult task

    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
     ego
    -0.10
     caring
    -0.09
     Bry
    -0.09
     Pearson
    -0.09
     altern
    -0.09
    ige
    -0.09
     reachable
    -0.08
    prep
    -0.08
    yan
    -0.08
     decre
    -0.08
    POSITIVE LOGITS
     task
    0.12
    /version
    0.11
     needle
    0.11
     puzz
    0.10
    asso
    0.10
    ,ID
    0.10
    task
    0.10
     thresh
    0.10
     overwhelming
    0.10
     Killer
    0.10
    Activations Density 0.006%

    No Known Activations