© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 78
    Prev
    Next
    INDEX
    Explanations

    measures, weighs, ranges, covers

    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
     nth
    -0.08
     rem
    -0.08
     ['./
    -0.08
     perv
    -0.07
    ãĢİ
    -0.07
     somehow
    -0.07
    idges
    -0.06
     twink
    -0.06
    amd
    -0.06
    "_
    -0.06
    POSITIVE LOGITS
     approximately
    0.24
     roughly
    0.19
     Approximately
    0.18
     ranging
    0.18
    0.16
    approximately
    0.16
     upwards
    0.16
    约
    0.16
     averaging
    0.15
     whopping
    0.15
    Activations Density 2.689%

    No Known Activations