© 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. 16550
    Prev
    Next
    INDEX
    Explanations

    poor, sad, brave

    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
     Danger
    -0.10
     smart
    -0.08
    oulder
    -0.08
    coop
    -0.08
     Underground
    -0.08
    charts
    -0.08
     resentment
    -0.08
    dish
    -0.08
    icos
    -0.07
     spoilers
    -0.07
    POSITIVE LOGITS
     souls
    0.22
     unfortunate
    0.21
     poor
    0.20
     unlucky
    0.17
     unsus
    0.17
     miserable
    0.17
     helpless
    0.16
     pathetic
    0.16
     Poor
    0.16
     attempts
    0.16
    Activations Density 0.021%

    No Known Activations