© 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. 32865
    Prev
    Next
    INDEX
    Explanations

    beginning

    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
    -going
    -0.12
    ove
    -0.11
    anoi
    -0.10
     gaz
    -0.10
     behalf
    -0.10
     /^(
    -0.10
    ocha
    -0.10
    dpi
    -0.10
    éro
    -0.10
    it
    -0.09
    POSITIVE LOGITS
    nings
    0.21
    /end
    0.14
    ning
    0.13
    inning
    0.13
    NING
    0.12
    nen
    0.11
     anew
    0.11
    nard
    0.10
    ner
    0.10
    ImageContext
    0.10
    Activations Density 0.054%

    No Known Activations