© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55871
    Prev
    Next
    INDEX
    Explanations

    in general, and X in particular

    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
    SCO
    -0.10
    endon
    -0.09
     typical
    -0.09
     Tracker
    -0.09
    unted
    -0.09
    sters
    -0.09
    aring
    -0.09
    .defaults
    -0.08
    akin
    -0.08
     uncovered
    -0.08
    POSITIVE LOGITS
     Private
    0.09
     lav
    0.08
     Dich
    0.08
    k
    0.08
     cop
    0.07
    kus
    0.07
     pleas
    0.07
    lav
    0.07
    TM
    0.07
    eph
    0.07
    Activations Density 0.015%

    No Known Activations