© 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. 90127
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating superlative or comparative states

    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
    aint
    -0.09
    oser
    -0.08
     rang
    -0.08
     serious
    -0.08
     melody
    -0.07
    HDR
    -0.07
    weg
    -0.07
    asses
    -0.07
     completely
    -0.07
     quite
    -0.07
    POSITIVE LOGITS
     simplest
    0.14
     poisonous
    0.12
     imaginary
    0.12
     nearest
    0.12
     smallest
    0.12
     surrounding
    0.11
     darkest
    0.11
     latter
    0.11
     cheapest
    0.11
     latest
    0.11
    Activations Density 0.011%

    No Known Activations