© 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. 7466
    Prev
    Next
    INDEX
    Explanations

    siblings and sisters

    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
    levelname
    -0.09
    ussen
    -0.09
     siblings
    -0.09
    Issues
    -0.09
    DSA
    -0.09
     Bashar
    -0.09
     Surrey
    -0.09
    -drop
    -0.08
     Family
    -0.08
    una
    -0.08
    POSITIVE LOGITS
     cousins
    0.11
     unrelated
    0.10
     Cous
    0.09
     niece
    0.09
     nie
    0.09
    !=(
    0.09
    "):↵
    0.09
     neph
    0.08
     deployed
    0.08
     pants
    0.08
    Activations Density 0.129%

    No Known Activations