© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4617
    Prev
    Next
    INDEX
    Explanations

    drive from

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aim
    -0.08
     protr
    -0.08
     sk
    -0.07
    OTH
    -0.07
     gid
    -0.07
    CF
    -0.07
    .hd
    -0.07
     Sa
    -0.07
     pcl
    -0.07
    acid
    -0.07
    POSITIVE LOGITS
     [âĢ¦]↵↵
    0.11
     [âĢ¦
    0.10
    anus
    0.09
    âĢ¦↵↵
    0.08
     cant
    0.08
     gén
    0.08
    avian
    0.08
     caps
    0.08
    .Java
    0.08
    âĢ¦↵
    0.08
    Activations Density 0.003%

    No Known Activations