© 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. 58756
    Prev
    Next
    INDEX
    Explanations

    choices and dilemmas

    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
    illi
    -0.09
    +h
    -0.09
    ICLES
    -0.08
    arse
    -0.08
     exec
    -0.08
    .detail
    -0.08
     HOWEVER
    -0.08
    eq
    -0.08
     Tops
    -0.08
    HI
    -0.08
    POSITIVE LOGITS
     choices
    0.14
     opportunity
    0.13
     dilemma
    0.12
    -options
    0.12
     options
    0.12
    Choices
    0.11
     ult
    0.11
    options
    0.11
     opportunities
    0.11
     presented
    0.10
    Activations Density 0.105%

    No Known Activations