© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90996
    Prev
    Next
    INDEX
    Explanations

    help, provide, highlight, guards, made, allow

    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
     both
    -0.17
     either
    -0.14
     BOTH
    -0.13
    both
    -0.12
     Both
    -0.12
     firstly
    -0.12
     EITHER
    -0.12
     Either
    -0.11
     både
    -0.11
     zwar
    -0.11
    POSITIVE LOGITS
     FUN
    0.13
     easier
    0.13
     outright
    0.12
     brag
    0.12
     frankly
    0.12
    prevent
    0.12
     prevents
    0.11
     potentially
    0.11
     hopefully
    0.11
     darn
    0.10
    Activations Density 0.320%

    No Known Activations