© 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. 3164
    Prev
    Next
    INDEX
    Explanations

    don't get me wrong

    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
     Madness
    -0.09
    UM
    -0.09
    acher
    -0.09
    antic
    -0.09
     insane
    -0.08
     imprisonment
    -0.08
    ester
    -0.08
     Dorm
    -0.08
    berry
    -0.08
    itin
    -0.08
    POSITIVE LOGITS
     compliment
    0.11
     fair
    0.11
     politely
    0.11
     respect
    0.10
     Sorry
    0.10
     bless
    0.10
     sounding
    0.10
     respected
    0.10
     gently
    0.09
     bueno
    0.09
    Activations Density 0.227%

    No Known Activations