© 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. 33339
    Prev
    Next
    INDEX
    Explanations

    little or no

    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
     persisted
    -0.10
     preempt
    -0.09
    ogie
    -0.09
    persist
    -0.09
    persistent
    -0.09
     persists
    -0.09
    cnt
    -0.09
     Roz
    -0.09
    uzzi
    -0.09
     viable
    -0.09
    POSITIVE LOGITS
     insignificant
    0.18
     manageable
    0.16
     modest
    0.15
     indirect
    0.13
     ineffective
    0.13
     subtle
    0.12
     humble
    0.12
     innoc
    0.12
     harmless
    0.12
    manage
    0.12
    Activations Density 0.060%

    No Known Activations