© 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. 4569
    Prev
    Next
    INDEX
    Explanations

    copy and references

    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
     cum
    -0.11
    Hide
    -0.11
    ehr
    -0.10
    ilt
    -0.10
     masse
    -0.10
    urement
    -0.10
     accumulation
    -0.10
     accum
    -0.10
     chauff
    -0.10
     \/
    -0.10
    POSITIVE LOGITS
     copy
    0.18
     copies
    0.17
     Copy
    0.15
     copying
    0.14
     copied
    0.14
    copy
    0.13
    .copy
    0.12
     ownership
    0.12
     Copies
    0.11
    copies
    0.11
    Activations Density 0.279%

    No Known Activations