© 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. 57391
    Prev
    Next
    INDEX
    Explanations

    US states

    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
    ibox
    -0.09
    ayas
    -0.09
    iane
    -0.09
    thalm
    -0.08
     spare
    -0.08
    /link
    -0.08
     collapsed
    -0.08
    urse
    -0.08
     NU
    -0.08
    -prefix
    -0.08
    POSITIVE LOGITS
     Clover
    0.08
     sire
    0.08
    оÐ
    0.08
     Rosen
    0.07
     suf
    0.07
     bib
    0.07
    ajs
    0.07
     Peg
    0.07
     Roz
    0.07
     Rab
    0.07
    Activations Density 0.086%

    No Known Activations