© 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. 132
    Prev
    Next
    INDEX
    Explanations

    title:

    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
    ster
    -0.08
    ory
    -0.08
    zos
    -0.08
    amba
    -0.07
    abled
    -0.07
    ller
    -0.07
     Herman
    -0.07
    cho
    -0.07
    STER
    -0.07
     Pakistani
    -0.07
    POSITIVE LOGITS
    =title
    0.10
    bild
    0.10
    /head
    0.10
    (title
    0.09
    Suffix
    0.09
    itat
    0.09
    algo
    0.09
    .locals
    0.09
     inf
    0.09
    holder
    0.09
    Activations Density 0.394%

    No Known Activations