© 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. 91697
    Prev
    Next
    INDEX
    Explanations

    necklaces and jewelry

    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
     duro
    -0.11
    anzi
    -0.10
    管
    -0.10
     Rif
    -0.10
    unda
    -0.10
    aldi
    -0.10
     inds
    -0.10
    berman
    -0.10
     smear
    -0.10
    FLAGS
    -0.09
    POSITIVE LOGITS
     necklace
    0.22
     pendant
    0.18
     chain
    0.17
     Necklace
    0.17
     neck
    0.16
     neckline
    0.16
     chains
    0.14
    -chain
    0.14
     Neck
    0.14
     hangs
    0.14
    Activations Density 0.113%

    No Known Activations