© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    new paragraph or list item opener

    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
     Clover
    -0.08
    jud
    -0.08
     However
    -0.08
     The
    -0.08
    zu
    -0.08
     Jud
    -0.07
    hana
    -0.07
     method
    -0.07
     binding
    -0.07
     adm
    -0.07
    POSITIVE LOGITS
     STILL
    0.11
     McCoy
    0.10
    sworth
    0.10
     klein
    0.09
    woke
    0.09
     ÅĽ
    0.09
     Pager
    0.09
    abouts
    0.09
    cript
    0.09
    AFX
    0.09
    Activations Density 0.209%

    No Known Activations