© 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. 58554
    Prev
    Next
    INDEX
    Explanations

    appelle

    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
    åı·
    -0.08
     Clement
    -0.07
    OLT
    -0.07
     Linden
    -0.07
     Blogger
    -0.07
    ipe
    -0.07
     Alert
    -0.07
     hele
    -0.07
     facult
    -0.07
    (xx
    -0.07
    POSITIVE LOGITS
    ék
    0.10
     Basin
    0.09
     Hague
    0.09
    nier
    0.09
     eff
    0.09
     assertNull
    0.09
    ardy
    0.09
    texture
    0.09
     defence
    0.09
    asio
    0.09
    Activations Density 0.011%

    No Known Activations