© 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. 16023
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    kt
    -0.09
     masc
    -0.09
     therein
    -0.08
     hull
    -0.08
     Hubb
    -0.08
    968
    -0.08
     polling
    -0.08
     Merc
    -0.08
     timeline
    -0.08
     fick
    -0.08
    POSITIVE LOGITS
    tog
    0.11
     Baum
    0.10
    -alist
    0.10
     beep
    0.10
    ospace
    0.10
    astr
    0.10
     Afr
    0.10
     gall
    0.10
    aque
    0.10
    WC
    0.10
    Activations Density 0.013%

    No Known Activations