© 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. 3468
    Prev
    Next
    INDEX
    Explanations

    ber followed by common 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
    rut
    -0.09
    zek
    -0.09
    PTION
    -0.09
    isz
    -0.08
    ims
    -0.08
    rice
    -0.08
    rup
    -0.08
    issen
    -0.08
     Virt
    -0.08
    rum
    -0.08
    POSITIVE LOGITS
    ardin
    0.10
    trand
    0.10
    odia
    0.09
    ardi
    0.09
    atem
    0.09
    ths
    0.08
    mand
    0.08
     ===>
    0.08
     dys
    0.08
    ard
    0.08
    Activations Density 0.174%

    No Known Activations