© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57001
    Prev
    Next
    INDEX
    Explanations

    academic citations

    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
    arpa
    -0.09
    ámara
    -0.08
    opp
    -0.08
    owell
    -0.08
     با
    -0.08
    ibs
    -0.08
    amenti
    -0.08
    ÑıÑĤ
    -0.07
     scars
    -0.07
    uegos
    -0.07
    POSITIVE LOGITS
    angu
    0.08
     verk
    0.08
    enschaft
    0.08
     Sele
    0.08
     Casting
    0.08
     Coco
    0.08
    ilon
    0.08
     Fo
    0.08
     scho
    0.08
     patron
    0.07
    Activations Density 0.004%

    No Known Activations