© 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. 57982
    Prev
    Next
    INDEX
    Explanations

    were to

    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
    Would
    -0.11
     Would
    -0.11
     would
    -0.11
     wouldn
    -0.11
     Wouldn
    -0.10
    s
    -0.10
    CO
    -0.10
    QUIT
    -0.09
    sar
    -0.09
    erable
    -0.09
    POSITIVE LOGITS
     to
    0.09
    inc
    0.08
     ness
    0.08
    eses
    0.08
    isoft
    0.08
    otte
    0.08
    innen
    0.08
    idon
    0.08
    âĤ¬âĦ¢
    0.08
     Ves
    0.07
    Activations Density 0.009%

    No Known Activations