© 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. 15134
    Prev
    Next
    INDEX
    Explanations

    `rest` or `rested`

    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
    tol
    -0.09
    fu
    -0.09
    thr
    -0.08
     bore
    -0.08
     DIY
    -0.08
    auer
    -0.08
     DI
    -0.08
     Tit
    -0.08
     thrilling
    -0.08
     ecstasy
    -0.08
    POSITIVE LOGITS
     rest
    0.25
     rested
    0.24
     resting
    0.23
     rests
    0.21
     Rest
    0.20
    rest
    0.19
    Rest
    0.18
    /rest
    0.17
    -rest
    0.17
     REST
    0.16
    Activations Density 0.029%

    No Known Activations