© 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. 3370
    Prev
    Next
    INDEX
    Explanations

    system, conditions, interactions, progress

    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
    .Options
    -0.10
    .only
    -0.10
     subrange
    -0.10
    .Parser
    -0.09
    .ActionListener
    -0.09
    ï¼īãĢģ
    -0.09
     frequ
    -0.09
    /etc
    -0.09
    /options
    -0.09
    jr
    -0.09
    POSITIVE LOGITS
     itself
    0.10
    which
    0.09
     which
    0.08
    alt
    0.08
     rel
    0.08
    ent
    0.08
    .
    0.07
     hom
    0.07
     "../../../
    0.07
    ãĢĤ
    0.07
    Activations Density 0.515%

    No Known Activations