© 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. 16322
    Prev
    Next
    INDEX
    Explanations

    forthcoming / upcoming events and predictions

    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
    ARB
    -0.10
    661
    -0.09
    ihan
    -0.09
    Tot
    -0.09
     nodeName
    -0.09
    terraform
    -0.09
    .alignment
    -0.09
    ãģ¿
    -0.08
     itemprop
    -0.08
    Snippet
    -0.08
    POSITIVE LOGITS
     will
    0.44
    will
    0.41
    ä¼ļ
    0.34
     WILL
    0.32
    Will
    0.31
     upcoming
    0.31
     бÑĥдеÑĤ
    0.30
     forthcoming
    0.30
     Will
    0.29
     tomorrow
    0.28
    Activations Density 1.391%

    No Known Activations