© 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. 29786
    Prev
    Next
    INDEX
    Explanations

    historical context

    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
    aber
    -0.10
     Hist
    -0.09
    aben
    -0.08
     desirable
    -0.08
    chia
    -0.08
    aban
    -0.08
     sprung
    -0.08
     mig
    -0.07
    /ext
    -0.07
    820
    -0.07
    POSITIVE LOGITS
     precedent
    0.19
     preced
    0.18
    -fiction
    0.16
     precedence
    0.16
     context
    0.15
     CONTEXT
    0.15
    /arch
    0.15
     fiction
    0.14
    preced
    0.14
    -context
    0.14
    Activations Density 0.072%

    No Known Activations