© 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. 61541
    Prev
    Next
    INDEX
    Explanations

    round to nearest

    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
     visually
    -0.08
     Grape
    -0.07
     liar
    -0.07
     consent
    -0.07
     tense
    -0.07
     cascade
    -0.07
     cent
    -0.07
     Prairie
    -0.07
     Schultz
    -0.07
     Cascade
    -0.07
    POSITIVE LOGITS
     entra
    0.10
    haft
    0.10
    rompt
    0.10
     Provid
    0.10
    .prevent
    0.10
    quine
    0.10
    lify
    0.09
    eneral
    0.09
    mnop
    0.09
     Blocked
    0.09
    Activations Density 0.004%

    No Known Activations