© 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. 57702
    Prev
    Next
    INDEX
    Explanations

    square root expressions

    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
     Herr
    -0.10
    mek
    -0.09
    onis
    -0.09
    hir
    -0.09
     perfect
    -0.09
    alli
    -0.08
    ÐŃ
    -0.08
    oni
    -0.08
     ste
    -0.08
     Ste
    -0.08
    POSITIVE LOGITS
     Memorial
    0.09
    .mit
    0.09
    nar
    0.08
    unto
    0.08
    ever
    0.07
    crets
    0.07
    loser
    0.07
     Monument
    0.07
     May
    0.07
    oded
    0.07
    Activations Density 0.005%

    No Known Activations