© 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. 58162
    Prev
    Next
    INDEX
    Explanations

    leaks and leakage detection

    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
    ment
    -0.12
     impro
    -0.10
    ting
    -0.10
     uninterrupted
    -0.09
    er
    -0.09
    cke
    -0.09
     Batter
    -0.09
     interchange
    -0.09
    Crypt
    -0.09
    ÑĤе
    -0.09
    POSITIVE LOGITS
    /qu
    0.10
    apat
    0.09
    afd
    0.08
    bau
    0.08
     posi
    0.08
     naughty
    0.08
     envelope
    0.08
    ä½ľèĢħ
    0.07
    -envelope
    0.07
    hunter
    0.07
    Activations Density 0.005%

    No Known Activations