© 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. 55533
    Prev
    Next
    INDEX
    Explanations

    precisely what

    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
     certainly
    -0.11
     Tango
    -0.10
     anyhow
    -0.09
     atleast
    -0.09
     unavoid
    -0.09
    omers
    -0.09
    ussen
    -0.09
     undoubtedly
    -0.09
    Zero
    -0.09
    osal
    -0.09
    POSITIVE LOGITS
    inky
    0.09
    hiba
    0.09
    Bid
    0.09
    ove
    0.08
     Bris
    0.08
    ree
    0.08
    enha
    0.08
    uppe
    0.08
    haft
    0.07
    opp
    0.07
    Activations Density 0.017%

    No Known Activations