© 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. 28024
    Prev
    Next
    INDEX
    Explanations

    purely, strictly, solely

    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
     Alive
    -0.11
     alive
    -0.10
    jal
    -0.10
     sentimental
    -0.09
     ordin
    -0.09
     worldly
    -0.09
    jang
    -0.08
    bour
    -0.08
    chia
    -0.08
    ieux
    -0.08
    POSITIVE LOGITS
     purely
    0.52
     pure
    0.50
    pure
    0.42
     strictly
    0.41
     Pure
    0.38
     truly
    0.37
    Pure
    0.36
     PURE
    0.34
     solely
    0.34
     fully
    0.33
    Activations Density 1.395%

    No Known Activations