© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61811
    Prev
    Next
    INDEX
    Explanations

    mood disorders, regulation, swings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    vel
    -0.09
     duk
    -0.09
    cia
    -0.09
     Slim
    -0.09
    argo
    -0.09
    belief
    -0.08
     cach
    -0.08
    peed
    -0.08
     preval
    -0.08
     Perkins
    -0.08
    POSITIVE LOGITS
    iness
    0.13
    ily
    0.11
    ary
    0.10
    ier
    0.10
     swings
    0.10
    nage
    0.09
     sour
    0.09
     compounded
    0.09
    ware
    0.08
     mood
    0.08
    Activations Density 0.003%

    No Known Activations