© 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. 58142
    Prev
    Next
    INDEX
    Explanations

    citation endings

    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
    allas
    -0.08
     GV
    -0.08
    ruk
    -0.08
     Bros
    -0.08
     PUBLIC
    -0.07
    ress
    -0.07
    esters
    -0.07
     lest
    -0.06
    ATEST
    -0.06
     eval
    -0.06
    POSITIVE LOGITS
    filt
    0.11
    kaar
    0.10
    bern
    0.10
     amb
    0.10
    .mapping
    0.10
    /AFP
    0.10
     respectively
    0.09
    oho
    0.09
    endance
    0.09
    yon
    0.09
    Activations Density 0.007%

    No Known Activations