© 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. 47200
    Prev
    Next
    INDEX
    Explanations

    people in distress

    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
     wield
    -0.13
     arrog
    -0.12
     meddling
    -0.11
     brib
    -0.11
     boring
    -0.11
     multip
    -0.11
     accredited
    -0.10
     clich
    -0.10
     cheat
    -0.10
     annoying
    -0.10
    POSITIVE LOGITS
     distressed
    0.37
     suffering
    0.34
     plight
    0.31
     needy
    0.31
     distress
    0.30
     struggling
    0.28
     distra
    0.27
     troubled
    0.27
     vulnerable
    0.26
     crying
    0.24
    Activations Density 0.262%

    No Known Activations