© 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. 47989
    Prev
    Next
    INDEX
    Explanations

    used to / used as

    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
    ovo
    -0.11
    697
    -0.10
    818
    -0.10
     owe
    -0.10
    oso
    -0.09
    kas
    -0.09
    218
    -0.09
    ffer
    -0.09
    496
    -0.09
    uder
    -0.09
    POSITIVE LOGITS
     as
    0.17
     sebagai
    0.14
     differently
    0.10
     als
    0.09
     pretext
    0.09
     comme
    0.09
     jako
    0.09
    ä½ľ
    0.09
     Coupons
    0.09
     serve
    0.09
    Activations Density 0.219%

    No Known Activations