© 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. 58119
    Prev
    Next
    INDEX
    Explanations

    study samples or groups

    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
    ?=
    -0.09
    aub
    -0.09
    olta
    -0.09
    enti
    -0.09
    inger
    -0.08
    ace
    -0.08
    zz
    -0.08
     Eval
    -0.08
     rear
    -0.07
     Harrison
    -0.07
    POSITIVE LOGITS
     Highly
    0.09
    ernet
    0.09
     polymer
    0.09
     highly
    0.09
    ooth
    0.08
    ettes
    0.08
    uess
    0.08
    ACTIVE
    0.08
    campo
    0.08
     exclus
    0.08
    Activations Density 0.296%

    No Known Activations