© 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. 4113
    Prev
    Next
    INDEX
    Explanations

    to or until a date

    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
    fare
    -0.10
    UDO
    -0.10
    uros
    -0.10
    ixo
    -0.10
     Consort
    -0.10
    ';↵↵↵↵
    -0.10
    aval
    -0.10
     screenSize
    -0.09
    alc
    -0.09
    ammo
    -0.09
    POSITIVE LOGITS
     interrupted
    0.08
    alla
    0.07
     cro
    0.07
     Cro
    0.07
    cz
    0.07
    âĢİ
    0.07
    rique
    0.07
    nl
    0.07
     impe
    0.07
     Dig
    0.06
    Activations Density 0.127%

    No Known Activations