© 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. 61605
    Prev
    Next
    INDEX
    Explanations

    names ending in -ong, -ung, -eng

    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
     unt
    -0.09
     Seal
    -0.09
    shiv
    -0.09
    HQ
    -0.08
    elli
    -0.08
     unb
    -0.08
    ording
    -0.08
    .setOutput
    -0.08
    ilia
    -0.08
     tir
    -0.08
    POSITIVE LOGITS
    inic
    0.08
     apprent
    0.08
     co
    0.08
    ergy
    0.08
    interrupt
    0.08
    åĬŁ
    0.08
    _contr
    0.08
     deferred
    0.07
    -
    0.07
    bourne
    0.07
    Activations Density 0.033%

    No Known Activations