© 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. 15431
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    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
    ly
    -0.15
    ness
    -0.10
     matte
    -0.10
    -era
    -0.09
    ise
    -0.09
    lys
    -0.09
    itty
    -0.09
    ely
    -0.09
    LY
    -0.08
    eer
    -0.08
    POSITIVE LOGITS
     eventual
    0.11
    Sharper
    0.10
    funcs
    0.09
    ï½¥
    0.08
    /cards
    0.08
    .priv
    0.08
     dak
    0.08
    -strokes
    0.08
     trä
    0.08
    iele
    0.07
    Activations Density 0.698%

    No Known Activations