© 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. 49601
    Prev
    Next
    INDEX
    Explanations

    specifically relevant

    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
     simply
    -0.16
     merely
    -0.15
     simplement
    -0.13
     juste
    -0.12
     zwar
    -0.11
     just
    -0.11
     surprisingly
    -0.10
     einfach
    -0.10
     anytime
    -0.09
     Lloyd
    -0.09
    POSITIVE LOGITS
     explicitly
    0.21
     expressly
    0.18
     specifically
    0.17
     explicit
    0.15
     Explicit
    0.15
     absolutely
    0.14
     beforehand
    0.14
    explicit
    0.13
     Specifically
    0.13
     actively
    0.13
    Activations Density 0.273%

    No Known Activations