© 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. 55041
    Prev
    Next
    INDEX
    Explanations

    number of people or capacity

    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
     ren
    -0.10
    ivr
    -0.09
    lifetime
    -0.09
    stdarg
    -0.09
    bsolute
    -0.08
     Hundred
    -0.08
    unsafe
    -0.08
    accum
    -0.08
     Mun
    -0.08
    ulty
    -0.08
    POSITIVE LOGITS
     blind
    0.10
    kar
    0.09
    iko
    0.09
     comfortably
    0.09
     Gross
    0.09
     traff
    0.09
     alternatively
    0.09
     dates
    0.08
     Kos
    0.08
     indirectly
    0.08
    Activations Density 0.032%

    No Known Activations