© 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. 2355
    Prev
    Next
    INDEX
    Explanations

    and then

    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
     ought
    -0.09
     win
    -0.08
    ides
    -0.08
     attendant
    -0.08
     anyway
    -0.08
    ooter
    -0.07
    onga
    -0.07
     Cors
    -0.07
     junk
    -0.07
    umper
    -0.07
    POSITIVE LOGITS
     also
    0.10
    ieties
    0.10
     thankfully
    0.10
     ironically
    0.09
     subsequently
    0.09
    omat
    0.09
     luckily
    0.09
     rightfully
    0.09
    also
    0.09
     quel
    0.09
    Activations Density 0.930%

    No Known Activations