© 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. 3228
    Prev
    Next
    INDEX
    Explanations

    subjects performing actions

    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
     responded
    -0.10
    una
    -0.09
     Respond
    -0.08
     responds
    -0.08
     respond
    -0.08
     response
    -0.08
    respond
    -0.07
     counter
    -0.07
     retali
    -0.07
     replied
    -0.07
    POSITIVE LOGITS
     thereby
    0.13
     damit
    0.12
     afterwards
    0.12
     wins
    0.11
     Earn
    0.11
     meant
    0.11
     hoped
    0.11
     pref
    0.11
     later
    0.11
     afterward
    0.11
    Activations Density 0.350%

    No Known Activations