© 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. 527
    Prev
    Next
    INDEX
    Explanations

    reacts or responds

    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
    /from
    -0.13
    /by
    -0.13
    /of
    -0.11
    oya
    -0.10
    ERTICAL
    -0.10
    /on
    -0.10
    .chapter
    -0.09
    iego
    -0.09
    @student
    -0.09
    fos
    -0.09
    POSITIVE LOGITS
     with
    0.15
    äºİ
    0.14
     into
    0.13
    /respond
    0.13
    /react
    0.13
     against
    0.12
     on
    0.12
     to
    0.11
    å¾Ĺ
    0.11
     through
    0.11
    Activations Density 1.976%

    No Known Activations