© 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. 4398
    Prev
    Next
    INDEX
    Explanations

    and able or bring or tell or ads or staging

    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
    uni
    -0.09
    esh
    -0.08
    —even
    -0.08
    vari
    -0.08
    ented
    -0.08
    lement
    -0.08
    bos
    -0.08
     Voll
    -0.08
    bere
    -0.07
     readline
    -0.07
    POSITIVE LOGITS
     etc
    0.10
     also
    0.10
     Its
    0.10
    "struct
    0.09
     equipments
    0.09
     it
    0.09
     its
    0.09
    akis
    0.09
     Also
    0.09
     signin
    0.09
    Activations Density 0.451%

    No Known Activations