© 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. 111793
    Prev
    Next
    INDEX
    Explanations

    but enough

    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
     barely
    -0.13
     lesser
    -0.12
     only
    -0.11
     scarcely
    -0.11
     harmless
    -0.11
     narrowly
    -0.11
     less
    -0.10
     LESS
    -0.10
     Lesser
    -0.10
     negligible
    -0.10
    POSITIVE LOGITS
     enough
    0.33
     Enough
    0.31
     sufficient
    0.25
    Enough
    0.22
     nonetheless
    0.19
     nevertheless
    0.18
     suffice
    0.17
     sufficiently
    0.16
     effective
    0.15
     suff
    0.15
    Activations Density 0.189%

    No Known Activations