© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    use this / citing or

    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
     stout
    -0.09
    undry
    -0.08
     Marty
    -0.08
     conserv
    -0.08
     Experienced
    -0.08
    iro
    -0.08
    kok
    -0.08
     mastering
    -0.08
     conventions
    -0.08
     conservatism
    -0.08
    POSITIVE LOGITS
     unless
    0.21
    unless
    0.18
     anything
    0.17
     ANY
    0.16
     knowingly
    0.16
     Unless
    0.15
     lest
    0.14
     any
    0.14
     unauthorized
    0.14
    anything
    0.14
    Activations Density 1.871%

    No Known Activations