© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    qualities of character

    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
    iers
    -0.11
    ordo
    -0.10
    uj
    -0.09
    onso
    -0.09
    ddl
    -0.09
    zi
    -0.09
    umd
    -0.09
    uit
    -0.08
    cht
    -0.08
     roughly
    -0.08
    POSITIVE LOGITS
    -minded
    0.19
     minded
    0.15
     enough
    0.14
    ness
    0.14
    -looking
    0.12
     and
    0.12
     yet
    0.11
    -thinking
    0.11
     thinking
    0.11
     approach
    0.10
    Activations Density 2.413%

    No Known Activations