© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    second occurrence

    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
     finally
    -0.09
     bus
    -0.08
     scrut
    -0.08
    alers
    -0.08
     asses
    -0.08
    aque
    -0.07
    overs
    -0.07
    ener
    -0.07
    akest
    -0.07
     overdue
    -0.07
    POSITIVE LOGITS
     similarly
    0.20
     another
    0.20
     equally
    0.20
    another
    0.17
     separately
    0.17
     second
    0.17
    second
    0.15
     Another
    0.14
     ebenfalls
    0.13
    Another
    0.13
    Activations Density 2.592%

    No Known Activations