© 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. 55307
    Prev
    Next
    INDEX
    Explanations

    names with suffixes

    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
    Accessible
    -0.10
     humble
    -0.09
     phased
    -0.09
    dep
    -0.09
    anh
    -0.09
     stamp
    -0.08
     Attr
    -0.08
     Chew
    -0.08
    vision
    -0.08
    ifter
    -0.08
    POSITIVE LOGITS
     multim
    0.08
    quot
    0.08
    itational
    0.08
    latex
    0.08
     Soft
    0.07
    ìĬ¤íĬ¸
    0.07
     workplace
    0.07
     cooper
    0.07
     Greg
    0.07
     cooperative
    0.07
    Activations Density 0.015%

    No Known Activations