© 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. 57754
    Prev
    Next
    INDEX
    Explanations

    honesty and 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
    lessness
    -0.10
    anim
    -0.09
    less
    -0.08
    azzi
    -0.08
     Dash
    -0.08
    iram
    -0.08
    star
    -0.08
    osa
    -0.08
    tery
    -0.08
     def
    -0.08
    POSITIVE LOGITS
     cade
    0.09
    tica
    0.08
    asley
    0.08
    arp
    0.08
    .ng
    0.08
    pipes
    0.08
    uments
    0.08
    -ticket
    0.08
    bsp
    0.08
    ACE
    0.08
    Activations Density 0.004%

    No Known Activations