© 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. 3502
    Prev
    Next
    INDEX
    Explanations

    questioning validity or truthfulness

    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
     siding
    -0.09
     minimized
    -0.09
     disin
    -0.08
    own
    -0.08
     tent
    -0.08
     gut
    -0.08
    cover
    -0.08
     unwilling
    -0.08
    cho
    -0.08
     invis
    -0.08
    POSITIVE LOGITS
     premise
    0.11
     actually
    0.11
     scientifically
    0.11
     actual
    0.10
     Actually
    0.10
    enco
    0.10
     validity
    0.10
     premises
    0.10
     basis
    0.10
     cites
    0.09
    Activations Density 0.242%

    No Known Activations