© 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. 16948
    Prev
    Next
    INDEX
    Explanations

    scouting and reconnaissance

    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
    ities
    -0.12
    hari
    -0.11
    etta
    -0.10
     hostages
    -0.10
     homic
    -0.10
    ysz
    -0.10
    anity
    -0.10
    jsc
    -0.10
    ople
    -0.10
    ottom
    -0.10
    POSITIVE LOGITS
     reconnaissance
    0.17
     scout
    0.16
     scouts
    0.15
     recon
    0.15
     Recon
    0.15
     ahead
    0.15
     Ahead
    0.14
    -ahead
    0.12
     pat
    0.12
     lookout
    0.12
    Activations Density 0.108%

    No Known Activations