© 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. 17001
    Prev
    Next
    INDEX
    Explanations

    landed or landing

    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
    andum
    -0.11
    678
    -0.11
    rosso
    -0.10
    atta
    -0.10
    villa
    -0.10
    redi
    -0.10
     nichts
    -0.10
    aims
    -0.10
    uur
    -0.10
    672
    -0.09
    POSITIVE LOGITS
     squarely
    0.15
     blows
    0.11
    fills
    0.10
     on
    0.10
     Landing
    0.10
    landing
    0.09
     landing
    0.09
     pages
    0.09
     safely
    0.09
     smack
    0.09
    Activations Density 0.019%

    No Known Activations