© 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. 2104
    Prev
    Next
    INDEX
    Explanations

    bolts, fasteners, holding

    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
     shedding
    -0.09
    ahead
    -0.08
     Tele
    -0.08
     convo
    -0.08
    Tele
    -0.08
    ella
    -0.08
    tele
    -0.08
     pushed
    -0.08
    (man
    -0.08
     sheds
    -0.08
    POSITIVE LOGITS
     strength
    0.12
     Bonds
    0.12
     bonds
    0.11
     bind
    0.11
     anch
    0.11
     binder
    0.11
     binding
    0.10
    iju
    0.10
    aira
    0.10
     strengths
    0.10
    Activations Density 0.289%

    No Known Activations