© 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. 89193
    Prev
    Next
    INDEX
    Explanations

    selection and browsing verbs

    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
    ief
    -0.10
     Tracker
    -0.09
     Zu
    -0.09
     anc
    -0.09
    hana
    -0.09
    anga
    -0.09
     Anc
    -0.08
    Filed
    -0.08
     celebr
    -0.08
     hoax
    -0.08
    POSITIVE LOGITS
     selection
    0.30
     selections
    0.29
     browsing
    0.29
     selecting
    0.28
     Selection
    0.27
     browse
    0.27
     Browse
    0.26
    selection
    0.25
    Selection
    0.24
     catalog
    0.23
    Activations Density 0.132%

    No Known Activations