© 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. 1243
    Prev
    Next
    INDEX
    Explanations

    (Material, median, test, analysis

    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
    /flutter
    -0.10
     Caj
    -0.09
    /orders
    -0.09
    /team
    -0.09
    expiry
    -0.08
    (async
    -0.08
    .Dynamic
    -0.08
    mph
    -0.08
    /front
    -0.08
    ид
    -0.08
    POSITIVE LOGITS
    (Material
    0.07
     nutrit
    0.07
    (preg
    0.07
    обÑĢаÐ
    0.07
     unins
    0.07
    pulse
    0.07
    SID
    0.07
     Maar
    0.07
    (MediaType
    0.06
     informat
    0.06
    Activations Density 4.477%

    No Known Activations