© 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. 48548
    Prev
    Next
    INDEX
    Explanations

    strengths, positives, and successes

    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
     quoted
    -0.11
    uhe
    -0.10
     dislike
    -0.10
    ataka
    -0.10
    unu
    -0.10
    359
    -0.10
    vero
    -0.10
     desp
    -0.10
     quotations
    -0.09
     requirement
    -0.09
    POSITIVE LOGITS
     strengths
    0.57
     Strength
    0.30
    Strength
    0.28
     positives
    0.26
     talents
    0.26
     assets
    0.26
    strength
    0.24
     strength
    0.24
     weaknesses
    0.24
     successes
    0.23
    Activations Density 0.177%

    No Known Activations