© 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. 48534
    Prev
    Next
    INDEX
    Explanations

    hold / holds / held / holding

    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
     Hunter
    -0.11
     ard
    -0.09
    Hold
    -0.09
     yak
    -0.09
    log
    -0.09
     Hold
    -0.09
    âĿ
    -0.09
     behind
    -0.08
    .prototype
    -0.08
     fier
    -0.08
    POSITIVE LOGITS
     sway
    0.15
    onto
    0.13
     onto
    0.12
    ogi
    0.12
    usan
    0.11
    >čč↵
    0.10
     Oliv
    0.10
     monopol
    0.10
     aba
    0.10
    Domin
    0.10
    Activations Density 0.057%

    No Known Activations