© 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. 58594
    Prev
    Next
    INDEX
    Explanations

    energy intake

    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
    horn
    -0.09
    itin
    -0.09
    itel
    -0.09
    inke
    -0.09
    eb
    -0.08
    ources
    -0.08
    lein
    -0.08
     replen
    -0.08
    iliar
    -0.08
     Ñģлед
    -0.08
    POSITIVE LOGITS
    /mac
    0.10
    atr
    0.09
    å®ļ
    0.09
     MACHINE
    0.09
    rex
    0.09
    .rate
    0.09
    attr
    0.09
    ABL
    0.09
    Attr
    0.08
     Neptune
    0.08
    Activations Density 0.010%

    No Known Activations