© 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. 56945
    Prev
    Next
    INDEX
    Explanations

    curative

    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
    es
    -0.14
    ess
    -0.10
    itivity
    -0.10
    eth
    -0.10
    esc
    -0.10
    ette
    -0.09
    ex
    -0.09
    adh
    -0.09
    alo
    -0.09
     veget
    -0.09
    POSITIVE LOGITS
    ating
    0.09
    ated
    0.09
    atorial
    0.09
    ments
    0.09
    vey
    0.08
     vitae
    0.08
     Bere
    0.08
    ates
    0.08
     appro
    0.08
    ATED
    0.08
    Activations Density 0.005%

    No Known Activations