© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8646
    Prev
    Next
    INDEX
    Explanations

    food items like chips, pizza

    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
     legitimately
    -0.07
     Pop
    -0.06
    Friend
    -0.06
    RGB
    -0.06
    Pop
    -0.06
     Prometheus
    -0.06
     Falk
    -0.06
    	getline
    -0.06
     Voyager
    -0.06
     Friend
    -0.06
    POSITIVE LOGITS
     plais
    0.10
    ecure
    0.10
    %");↵
    0.10
     general
    0.10
    -Regular
    0.10
    -equiv
    0.10
     General
    0.10
     rien
    0.10
    inherits
    0.10
    irit
    0.09
    Activations Density 0.296%

    No Known Activations