© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 4259
    Prev
    Next
    INDEX
    Explanations

    related to exceptions

    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
    иÑĩ
    -0.09
     extent
    -0.08
    oron
    -0.08
    INGTON
    -0.08
     Wahl
    -0.08
    stry
    -0.08
     schwar
    -0.08
    hen
    -0.08
    hl
    -0.08
    ros
    -0.08
    POSITIVE LOGITS
    ively
    0.12
    ally
    0.11
    ality
    0.11
    al
    0.10
    иÑĤелÑĮ
    0.10
     cref
    0.10
    ant
    0.09
    alty
    0.09
     hottest
    0.09
    /un
    0.09
    Activations Density 0.095%

    No Known Activations