© 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. 56672
    Prev
    Next
    INDEX
    Explanations

    Thomaston, Hallman, Tesco, Allied, Evanston

    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
     nb
    -0.09
    Collapse
    -0.09
    <![
    -0.08
     Boutique
    -0.08
    nea
    -0.07
    isan
    -0.07
     Bucc
    -0.07
    amping
    -0.07
     Econom
    -0.07
    Coupon
    -0.07
    POSITIVE LOGITS
     quo
    0.10
    lut
    0.10
    âĢ¦the
    0.09
    lug
    0.09
     Pend
    0.09
    kom
    0.09
     Shar
    0.09
    icie
    0.08
    ENO
    0.08
    Stored
    0.08
    Activations Density 0.029%

    No Known Activations