© 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. 56540
    Prev
    Next
    INDEX
    Explanations

    Risks, Various, This, The, Personal, Our

    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
     Rub
    -0.09
     Culture
    -0.08
     Autor
    -0.08
     triggers
    -0.08
     Recently
    -0.08
    :Object
    -0.08
     Loc
    -0.08
    pone
    -0.08
    jam
    -0.08
     LESS
    -0.08
    POSITIVE LOGITS
    ä»ĺ
    0.11
    too
    0.09
    æĸ
    0.09
    tool
    0.08
     specialize
    0.08
     stroke
    0.08
     formal
    0.08
    Spaces
    0.08
     Titles
    0.08
    anza
    0.08
    Activations Density 0.123%

    No Known Activations