© 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. 7820
    Prev
    Next
    INDEX
    Explanations

    demonstration or audition

    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
     federally
    -0.10
     accus
    -0.10
    092
    -0.10
    PCS
    -0.09
     belle
    -0.09
     wid
    -0.09
    Illegal
    -0.09
     invalidate
    -0.09
     Emp
    -0.08
    Emp
    -0.08
    POSITIVE LOGITS
     prove
    0.25
     proving
    0.24
     audition
    0.22
     demonstration
    0.21
     demonstrated
    0.21
     demonstrate
    0.20
     proves
    0.20
     proved
    0.20
     demonstrating
    0.20
     Demonstr
    0.18
    Activations Density 0.060%

    No Known Activations