© 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. 89963
    Prev
    Next
    INDEX
    Explanations

    list, express, four, package

    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
     quat
    -0.09
     Desc
    -0.09
    ÑģÑı
    -0.08
     cate
    -0.08
     interp
    -0.08
     seal
    -0.08
     ple
    -0.08
     Lennon
    -0.07
     Symphony
    -0.07
    iad
    -0.07
    POSITIVE LOGITS
    cé
    0.13
     Bailey
    0.12
    Ash
    0.11
    né
    0.11
    ĶåĽŀ
    0.10
    axed
    0.10
     Ash
    0.10
    -deals
    0.10
     ash
    0.10
     peacefully
    0.10
    Activations Density 0.011%

    No Known Activations