© 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. 4066
    Prev
    Next
    INDEX
    Explanations

    previously asked

    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
    ruk
    -0.10
    ograms
    -0.10
     increasingly
    -0.10
     Modern
    -0.09
     Latest
    -0.09
     ups
    -0.09
    agram
    -0.09
     preceded
    -0.09
     whats
    -0.09
    iew
    -0.08
    POSITIVE LOGITS
     then
    0.19
    then
    0.18
     THEN
    0.16
     back
    0.16
     remembers
    0.15
     originally
    0.15
     alors
    0.15
     remember
    0.15
     entonces
    0.15
     intervening
    0.14
    Activations Density 0.976%

    No Known Activations