© 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. 4565
    Prev
    Next
    INDEX
    Explanations

    config followed by name or for

    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
     pat
    -0.09
    ech
    -0.09
    ang
    -0.09
    ingle
    -0.09
    chal
    -0.09
     Pat
    -0.09
     Falk
    -0.08
    iffe
    -0.08
    aja
    -0.08
    achs
    -0.08
    POSITIVE LOGITS
    urable
    0.19
    urations
    0.16
    uring
    0.14
    urat
    0.13
    ures
    0.13
    urer
    0.13
    urt
    0.11
    urers
    0.11
    URATION
    0.11
    urate
    0.11
    Activations Density 0.118%

    No Known Activations