© 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. 3090
    Prev
    Next
    INDEX
    Explanations

    probability calculations with counts

    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
     unst
    -0.10
    омеÑĢ
    -0.09
    portal
    -0.09
     extrem
    -0.09
    ocr
    -0.09
    WD
    -0.09
    inel
    -0.09
     wik
    -0.09
    mers
    -0.08
     ex
    -0.08
    POSITIVE LOGITS
     candid
    0.08
     society
    0.08
    outh
    0.08
    'es
    0.07
     coping
    0.07
     bipolar
    0.07
    ONUS
    0.07
    assa
    0.07
     Society
    0.07
    ypical
    0.07
    Activations Density 0.010%

    No Known Activations