© 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. 55426
    Prev
    Next
    INDEX
    Explanations

    Egyptian mongoose

    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
     Tour
    -0.11
     Nose
    -0.10
     Busy
    -0.10
     Platz
    -0.09
    noc
    -0.09
    sto
    -0.09
    ares
    -0.09
    [at
    -0.09
     Laure
    -0.09
     Auch
    -0.09
    POSITIVE LOGITS
     kidd
    0.08
    enge
    0.07
    asher
    0.07
    achs
    0.07
     allev
    0.06
     prep
    0.06
    Updated
    0.06
    enci
    0.06
    vak
    0.06
     dope
    0.06
    Activations Density 0.003%

    No Known Activations