© 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. 57571
    Prev
    Next
    INDEX
    Explanations

    effect of

    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
    fell
    -0.07
     caused
    -0.07
    zo
    -0.07
    /react
    -0.07
    pe
    -0.07
     use
    -0.06
    /util
    -0.06
     manifestations
    -0.06
    ting
    -0.06
     seedu
    -0.06
    POSITIVE LOGITS
    edo
    0.11
    osi
    0.10
    oger
    0.10
    auc
    0.10
    orate
    0.10
    iska
    0.10
    -spacing
    0.10
    laws
    0.10
     Rib
    0.10
    ouch
    0.09
    Activations Density 0.065%

    No Known Activations