© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    identifier name or variable

    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
    oten
    -0.09
     Jen
    -0.08
    bulk
    -0.08
    jah
    -0.08
    essa
    -0.08
    __.__
    -0.08
    anax
    -0.08
    osa
    -0.08
    /apps
    -0.08
     Vib
    -0.08
    POSITIVE LOGITS
     colle
    0.10
    uf
    0.09
     plac
    0.09
     conc
    0.08
     po
    0.08
    erva
    0.08
    buff
    0.08
    pl
    0.08
    ãģĿ
    0.08
     rede
    0.08
    Activations Density 0.057%

    No Known Activations