© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE html

    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
    isti
    -0.09
    iamo
    -0.08
    ist
    -0.08
     dét
    -0.08
     fid
    -0.08
    ains
    -0.08
     properly
    -0.08
    uttle
    -0.08
    ork
    -0.08
    EDGE
    -0.08
    POSITIVE LOGITS
     sleeps
    0.10
    ernal
    0.09
    nas
    0.09
     coma
    0.09
    stead
    0.08
    wers
    0.08
    unan
    0.08
    Boxes
    0.08
    pus
    0.08
     Rei
    0.08
    Activations Density 0.001%

    No Known Activations