© 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. 54284
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    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
     deduct
    -0.09
     carve
    -0.08
     acad
    -0.08
     deducted
    -0.08
     spare
    -0.08
     Lau
    -0.08
    yan
    -0.08
    programming
    -0.07
     Bau
    -0.07
    g
    -0.07
    POSITIVE LOGITS
     imp
    0.10
    dea
    0.10
    quina
    0.10
    .tele
    0.10
     propaganda
    0.10
     obscure
    0.10
    ktop
    0.09
     obscured
    0.09
    alth
    0.09
     announcements
    0.09
    Activations Density 0.064%

    No Known Activations