© 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. 3855
    Prev
    Next
    INDEX
    Explanations

    debunking or refuting claims

    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
     ideally
    -0.08
     Ach
    -0.07
     Paige
    -0.07
    iego
    -0.07
    otta
    -0.07
    akov
    -0.07
     Baxter
    -0.07
     Observatory
    -0.07
    unky
    -0.07
    eti
    -0.07
    POSITIVE LOGITS
     contrary
    0.27
     Contr
    0.21
    Contr
    0.20
    contra
    0.19
     debunk
    0.18
     contradict
    0.18
     myth
    0.17
     misconception
    0.17
     contra
    0.16
     contrad
    0.16
    Activations Density 0.267%

    No Known Activations