© 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. 49628
    Prev
    Next
    INDEX
    Explanations

    elastic properties and rebounds

    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
     crane
    -0.11
    pour
    -0.10
     hitch
    -0.10
     Crane
    -0.10
    /meta
    -0.09
    lea
    -0.09
     grind
    -0.09
    Spoiler
    -0.09
     Vega
    -0.08
    arias
    -0.08
    POSITIVE LOGITS
     rebound
    0.30
     bounce
    0.28
     bounced
    0.26
     bouncing
    0.26
     rebounds
    0.25
     elastic
    0.22
     elasticity
    0.22
     recoil
    0.22
     spring
    0.21
    elastic
    0.20
    Activations Density 0.185%

    No Known Activations