© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    are often/used/typically

    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
     itself
    -0.29
     коÑĤоÑĢÑĭй
    -0.16
     was
    -0.12
    /is
    -0.11
    —a
    -0.11
     wasn
    -0.10
    —it
    -0.10
     its
    -0.09
     foremost
    -0.09
     two
    -0.09
    POSITIVE LOGITS
     themselves
    0.45
     thems
    0.21
     ones
    0.18
     yourselves
    0.18
     are
    0.14
    ones
    0.14
     collectively
    0.14
     their
    0.14
     alike
    0.14
     Ones
    0.13
    Activations Density 6.217%

    No Known Activations