© 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. 53734
    Prev
    Next
    INDEX
    Explanations

    alcoholic beverages

    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
     convincing
    -0.09
     inflated
    -0.08
    va
    -0.07
     Top
    -0.07
    ITOR
    -0.07
    tuple
    -0.07
     Darkness
    -0.07
     inflate
    -0.07
    anager
    -0.07
     hom
    -0.06
    POSITIVE LOGITS
     Bridges
    0.11
     Lonely
    0.10
    illance
    0.09
    rang
    0.09
     keen
    0.09
    avity
    0.09
    mour
    0.09
    iod
    0.09
    clr
    0.09
    NIL
    0.09
    Activations Density 0.011%

    No Known Activations