© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57859
    Prev
    Next
    INDEX
    Explanations

    ignore or exclude

    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
    defaults
    -0.09
     Dial
    -0.08
     Recomm
    -0.08
     dial
    -0.07
    chema
    -0.07
     Cornel
    -0.07
     Cond
    -0.07
    Gem
    -0.07
    rest
    -0.07
     defaults
    -0.07
    POSITIVE LOGITS
    iona
    0.10
     Ming
    0.10
    Cart
    0.09
     Tyr
    0.09
     cá
    0.09
    antly
    0.09
     altogether
    0.09
     mechan
    0.09
     Rivera
    0.09
    Temp
    0.09
    Activations Density 0.052%

    No Known Activations