© 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. 55598
    Prev
    Next
    INDEX
    Explanations

    capacity to

    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
    ared
    -0.10
    lier
    -0.09
    lingen
    -0.08
    éĴ®
    -0.08
    apter
    -0.08
    ÑģÑı
    -0.08
    Ur
    -0.08
    lust
    -0.08
    stones
    -0.08
    eric
    -0.08
    POSITIVE LOGITS
    ity
    0.13
    es
    0.13
    ical
    0.11
    emu
    0.11
    ees
    0.10
    erve
    0.10
    ient
    0.10
    uum
    0.10
    ally
    0.10
    imate
    0.10
    Activations Density 0.007%

    No Known Activations