© 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. 593
    Prev
    Next
    INDEX
    Explanations

    22 and Hawkins

    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
    or
    -0.10
    ÑĤ
    -0.10
    ening
    -0.10
    	↵	↵
    -0.09
    Ñı
    -0.08
    к
    -0.08
    orary
    -0.08
    iful
    -0.08
    .AC
    -0.08
    ity
    -0.08
    POSITIVE LOGITS
    ally
    0.13
    lette
    0.11
    ries
    0.11
    наÑĩ
    0.10
    engo
    0.10
    ings
    0.09
    otec
    0.09
    ality
    0.09
    nement
    0.09
    ets
    0.09
    Activations Density 4.674%

    No Known Activations