© 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. 16079
    Prev
    Next
    INDEX
    Explanations

    plan to, work with, scope to

    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
     bead
    -0.09
     mon
    -0.08
    arian
    -0.08
    ereg
    -0.08
     Randy
    -0.07
     Vincent
    -0.07
    .sc
    -0.07
    659
    -0.07
    .app
    -0.07
    dere
    -0.07
    POSITIVE LOGITS
     asÃŃ
    0.13
     behaved
    0.12
     behaves
    0.12
     behave
    0.12
     Kore
    0.11
     behaving
    0.11
    iol
    0.11
     ainsi
    0.11
    uts
    0.10
     approached
    0.10
    Activations Density 0.170%

    No Known Activations