© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89993
    Prev
    Next
    INDEX
    Explanations

    borderlands or border crossings

    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
     stal
    -0.08
    ÃŃst
    -0.08
    burn
    -0.08
    alte
    -0.08
    tes
    -0.08
    istic
    -0.08
    eler
    -0.08
    nes
    -0.08
     Loren
    -0.08
     Lear
    -0.08
    POSITIVE LOGITS
    lands
    0.16
    lines
    0.14
    (Border
    0.14
     crossings
    0.14
    LayoutPanel
    0.14
     patrol
    0.14
    cry
    0.13
    -cross
    0.13
     crossing
    0.12
    less
    0.12
    Activations Density 0.033%

    No Known Activations