© 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. 57858
    Prev
    Next
    INDEX
    Explanations

    alteration of

    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
    s
    -0.11
    ly
    -0.10
    iable
    -0.09
    ary
    -0.08
    bet
    -0.08
    loth
    -0.08
    arily
    -0.08
    ernet
    -0.08
    TEL
    -0.07
    kie
    -0.07
    POSITIVE LOGITS
    åĵģ
    0.12
    iban
    0.10
     vo
    0.10
    ubes
    0.10
    ation
    0.10
    edo
    0.10
    emo
    0.10
    aura
    0.10
    enties
    0.10
    ogy
    0.10
    Activations Density 0.011%

    No Known Activations