© 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. 57104
    Prev
    Next
    INDEX
    Explanations

    rank and degree values

    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
    eya
    -0.09
    arges
    -0.09
    crit
    -0.09
    zes
    -0.09
    LoginPage
    -0.08
    estre
    -0.08
     Wired
    -0.08
    ngle
    -0.08
     lob
    -0.08
     wired
    -0.08
    POSITIVE LOGITS
    wing
    0.09
     Nationals
    0.08
     Saunders
    0.08
    umba
    0.08
     Ful
    0.08
     chr
    0.08
    utter
    0.08
     \↵
    0.08
     Ahead
    0.08
    observ
    0.08
    Activations Density 0.023%

    No Known Activations