© 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. 31662
    Prev
    Next
    INDEX
    Explanations

    search queries and lookup

    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
     unpublished
    -0.11
     unt
    -0.10
     whims
    -0.10
     Antar
    -0.10
     eagle
    -0.10
     alternate
    -0.10
    clipboard
    -0.09
    localized
    -0.09
     Clipboard
    -0.09
    ackers
    -0.09
    POSITIVE LOGITS
     google
    0.19
     Google
    0.17
     search
    0.17
     youtube
    0.17
     YouTube
    0.17
    google
    0.16
     GOOGLE
    0.16
     Search
    0.15
     lookup
    0.15
    .google
    0.14
    Activations Density 0.092%

    No Known Activations