© 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. 8906
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No. issued

    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
     sco
    -0.11
    Transparent
    -0.10
     scoop
    -0.09
     Russ
    -0.09
     stuff
    -0.09
    elt
    -0.09
     cas
    -0.09
     Trailer
    -0.08
    esse
    -0.08
    enne
    -0.08
    POSITIVE LOGITS
    (App
    0.09
     Holland
    0.07
     Hawk
    0.07
    è¾¾
    0.07
     nad
    0.07
    Links
    0.07
    ,bool
    0.07
    ailable
    0.07
    ichen
    0.06
    ámara
    0.06
    Activations Density 0.022%

    No Known Activations