© 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. 58391
    Prev
    Next
    INDEX
    Explanations

    numbers and other identifiers

    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
     overshadow
    -0.07
    Canon
    -0.07
    Actual
    -0.07
     lesser
    -0.07
     actual
    -0.07
     till
    -0.06
    actual
    -0.06
    inic
    -0.06
     attracting
    -0.06
     Actual
    -0.06
    POSITIVE LOGITS
    -tags
    0.10
    ,),↵
    0.10
    YW
    0.10
     dipl
    0.10
     Protective
    0.09
    umerator
    0.09
    ento
    0.09
    ennes
    0.09
     ['./
    0.09
    ÃŃm
    0.09
    Activations Density 0.002%

    No Known Activations