© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    numbers followed by '/' or ')'

    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
     inj
    -0.10
    -0.08
    anka
    -0.08
    edo
    -0.08
    far
    -0.08
     meeting
    -0.07
     attendance
    -0.07
    dash
    -0.07
    orum
    -0.07
     Basil
    -0.07
    POSITIVE LOGITS
    -interface
    0.09
    intl
    0.09
    amac
    0.09
     Clarence
    0.09
    rive
    0.09
    uml
    0.09
    DDD
    0.09
    ook
    0.08
    Ŀ
    0.08
    /browse
    0.08
    Activations Density 0.272%

    No Known Activations