© 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. 56169
    Prev
    Next
    INDEX
    Explanations

    comparison words like as or like

    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
    CTX
    -0.08
     Swords
    -0.08
     lic
    -0.08
     Torch
    -0.07
     Arnold
    -0.07
     nomin
    -0.07
     cit
    -0.07
     specificity
    -0.07
     Yan
    -0.07
    lington
    -0.07
    POSITIVE LOGITS
     mirrored
    0.13
     mirrors
    0.12
     mirror
    0.12
    Lik
    0.12
     Correspond
    0.12
     reflects
    0.12
     mir
    0.12
     reflect
    0.11
    reflect
    0.11
     corresponding
    0.11
    Activations Density 0.090%

    No Known Activations