© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    forwarded

    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
    алÑĮ
    -0.08
    quiv
    -0.08
    Framework
    -0.07
    аÑĤелÑĮ
    -0.07
    auty
    -0.06
    ographic
    -0.06
    fed
    -0.06
    AL
    -0.06
    dl
    -0.06
    framework
    -0.06
    POSITIVE LOGITS
    ly
    0.15
    -thinking
    0.14
    -looking
    0.13
    ?family
    0.13
    -facing
    0.13
    mente
    0.13
    /down
    0.12
    itizer
    0.12
    ship
    0.11
    Cfg
    0.11
    Activations Density 0.193%

    No Known Activations