© 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. 116164
    Prev
    Next
    INDEX
    Explanations

    youngest to oldest family members

    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
     acquaintance
    -0.10
     Mentor
    -0.09
     acquaint
    -0.09
    elong
    -0.09
     generations
    -0.09
    apon
    -0.09
     dimensional
    -0.09
     partnering
    -0.09
     uncle
    -0.09
     families
    -0.09
    POSITIVE LOGITS
     eldest
    0.28
     youngest
    0.27
     twins
    0.24
     oldest
    0.24
     younger
    0.19
     daughters
    0.18
     Twins
    0.17
     older
    0.17
     elder
    0.15
     smallest
    0.15
    Activations Density 0.117%

    No Known Activations