© 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. 57914
    Prev
    Next
    INDEX
    Explanations

    loop index `i`

    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
    HQ
    -0.09
    visor
    -0.09
    /ts
    -0.08
    entina
    -0.08
    ogue
    -0.08
    icode
    -0.08
    bul
    -0.08
    zie
    -0.08
    ENS
    -0.08
    "is
    -0.08
    POSITIVE LOGITS
    eled
    0.11
     insets
    0.10
    AMED
    0.09
     pois
    0.09
    olars
    0.09
    Ñĥж
    0.08
    yan
    0.08
     Dun
    0.08
    enan
    0.08
    realm
    0.08
    Activations Density 0.004%

    No Known Activations