© 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. 115272
    Prev
    Next
    INDEX
    Explanations

    certain words followed by modifiers

    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
    'o
    -0.11
     resides
    -0.11
     Includes
    -0.11
     reside
    -0.11
     anyway
    -0.11
    includes
    -0.11
    Includes
    -0.11
     rests
    -0.10
    .Ab
    -0.10
    465
    -0.10
    POSITIVE LOGITS
     can
    0.18
     tends
    0.15
     may
    0.14
     offers
    0.14
     might
    0.13
     often
    0.12
     tend
    0.12
     generally
    0.12
     works
    0.11
     greatly
    0.11
    Activations Density 0.339%

    No Known Activations