© 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. 57543
    Prev
    Next
    INDEX
    Explanations

    related to external factors

    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
     also
    -0.14
     ALSO
    -0.14
    also
    -0.12
    Also
    -0.11
     STILL
    -0.10
    ãģ§ãĤĤ
    -0.10
     Also
    -0.10
    ä¹Ł
    -0.09
     auch
    -0.09
     ook
    -0.09
    POSITIVE LOGITS
     indirectly
    0.17
     indirect
    0.13
     Weird
    0.11
     elsewhere
    0.11
     Brent
    0.10
    ord
    0.09
    orp
    0.09
     tightly
    0.09
     unrelated
    0.09
     altogether
    0.08
    Activations Density 0.124%

    No Known Activations