© 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. 57551
    Prev
    Next
    INDEX
    Explanations

    unique values or identifiers

    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
     unique
    -0.12
     uniquely
    -0.12
    Unique
    -0.11
     uniqueness
    -0.10
     Unique
    -0.10
    _UNIQUE
    -0.09
    ģ
    -0.09
    íĬ
    -0.09
    unique
    -0.09
    aries
    -0.09
    POSITIVE LOGITS
    gam
    0.10
    edom
    0.09
    kah
    0.09
    cen
    0.09
    LOT
    0.09
     shocking
    0.08
    Anonymous
    0.08
    orz
    0.08
     suggestion
    0.08
    kö
    0.08
    Activations Density 0.010%

    No Known Activations