© 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. 3371
    Prev
    Next
    INDEX
    Explanations

    .tm

    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
     Abrams
    -0.09
     Ple
    -0.09
     hoop
    -0.09
    .ToShort
    -0.08
    INO
    -0.08
    <↵
    -0.08
     hikes
    -0.08
    abe
    -0.07
    ktop
    -0.07
    Mo
    -0.07
    POSITIVE LOGITS
    InMillis
    0.12
    oglob
    0.11
    dj
    0.10
    LF
    0.10
     Reporting
    0.09
     reporting
    0.09
    .Report
    0.09
     //{
    0.09
    -report
    0.08
    DSP
    0.08
    Activations Density 0.202%

    No Known Activations