© 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. 114742
    Prev
    Next
    INDEX
    Explanations

    great 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
     decent
    -0.11
     sane
    -0.11
     moderately
    -0.10
     slightly
    -0.10
     reasonably
    -0.10
     mildly
    -0.09
     apt
    -0.08
     sincere
    -0.08
     worthwhile
    -0.08
     respectfully
    -0.08
    POSITIVE LOGITS
     flashy
    0.14
     spectacular
    0.13
    either
    0.13
     either
    0.12
    efa
    0.12
     wow
    0.12
     blockbuster
    0.12
     extraordinary
    0.12
     exceptional
    0.12
     stellar
    0.12
    Activations Density 0.049%

    No Known Activations