© 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. 113712
    Prev
    Next
    INDEX
    Explanations

    awareness and sensing

    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
     kay
    -0.10
     intermittent
    -0.10
     motions
    -0.10
     Elliot
    -0.10
     strategic
    -0.09
    iline
    -0.09
     potions
    -0.09
     nons
    -0.09
     endanger
    -0.09
     Strategic
    -0.09
    POSITIVE LOGITS
     senses
    0.17
     sensing
    0.16
     probes
    0.16
     probing
    0.15
     probe
    0.15
     Probe
    0.14
    probe
    0.12
     mental
    0.12
     reconnaissance
    0.12
     mentally
    0.11
    Activations Density 0.096%

    No Known Activations