© 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. 88477
    Prev
    Next
    INDEX
    Explanations

    help myself

    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
     Circ
    -0.10
     thankfully
    -0.09
    uset
    -0.09
     plais
    -0.09
    rite
    -0.09
    .lv
    -0.09
    aly
    -0.09
     luckily
    -0.09
    .erb
    -0.08
     tact
    -0.08
    POSITIVE LOGITS
     soon
    0.18
    soon
    0.17
     imminent
    0.14
     impending
    0.14
    Soon
    0.13
     shortly
    0.13
     Soon
    0.13
     gonna
    0.12
     unavoid
    0.11
    onna
    0.10
    Activations Density 0.001%

    No Known Activations