© 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. 25609
    Prev
    Next
    INDEX
    Explanations

    behind or background

    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
    alm
    -0.10
     repl
    -0.09
    zek
    -0.09
    isel
    -0.09
     Bloom
    -0.09
     pref
    -0.08
     Jord
    -0.08
    ante
    -0.08
    prefix
    -0.08
     prefixed
    -0.08
    POSITIVE LOGITS
     behind
    0.57
     Behind
    0.49
    Behind
    0.45
     background
    0.34
    beh
    0.33
     backdrop
    0.29
     Background
    0.29
     backgrounds
    0.27
    background
    0.27
     BACKGROUND
    0.27
    Activations Density 0.141%

    No Known Activations