© 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. 32584
    Prev
    Next
    INDEX
    Explanations

    "" followed by sentences

    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
     gotta
    -0.12
    etta
    -0.10
     Manning
    -0.10
     shorthand
    -0.09
    elan
    -0.09
     Mour
    -0.09
    (and
    -0.09
    bd
    -0.09
    agh
    -0.09
    EDIT
    -0.08
    POSITIVE LOGITS
     Features
    0.13
    Therefore
    0.12
     Nowadays
    0.12
     nowadays
    0.12
    Features
    0.11
     Adv
    0.11
    Moreover
    0.11
     features
    0.11
     Importance
    0.11
    Nevertheless
    0.11
    Activations Density 0.038%

    No Known Activations