© 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. 33102
    Prev
    Next
    INDEX
    Explanations

    persistent thoughts or feelings

    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
     intimid
    -0.13
    panic
    -0.12
     scares
    -0.11
     fright
    -0.11
     happily
    -0.10
     proudly
    -0.10
     Pain
    -0.10
     reassure
    -0.10
     sob
    -0.10
     Pane
    -0.09
    POSITIVE LOGITS
     obsess
    0.22
     obsessed
    0.20
     obsession
    0.18
     incess
    0.17
     persistent
    0.16
     haunted
    0.16
     obsessive
    0.16
     repeatedly
    0.16
     persist
    0.15
     curiosity
    0.14
    Activations Density 0.074%

    No Known Activations