© 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. 2597
    Prev
    Next
    INDEX
    Explanations

    eating disorders self-esteem

    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
    plaint
    -0.10
     blindly
    -0.10
     patented
    -0.09
     waving
    -0.09
     blind
    -0.09
    plug
    -0.09
     plug
    -0.09
     illum
    -0.09
     benefiting
    -0.09
    .plot
    -0.09
    POSITIVE LOGITS
     competitiveness
    0.10
     perfection
    0.10
    fea
    0.10
    /self
    0.10
     inse
    0.09
     replay
    0.09
     feelings
    0.09
    -esteem
    0.09
     Self
    0.09
     achie
    0.08
    Activations Density 0.178%

    No Known Activations