© 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. 168
    Prev
    Next
    INDEX
    Explanations

    introduces consequence or conclusion

    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
     meanwhile
    -0.10
    pin
    -0.09
     because
    -0.09
    because
    -0.08
     _______,
    -0.08
     cuz
    -0.08
     Pin
    -0.08
     myster
    -0.07
     mirac
    -0.07
    esen
    -0.07
    POSITIVE LOGITS
     naturally
    0.15
     unsur
    0.13
     inevitably
    0.12
    forth
    0.12
     doubly
    0.12
     concludes
    0.12
     understandably
    0.12
     conclude
    0.11
     need
    0.11
     inevitable
    0.11
    Activations Density 1.421%

    No Known Activations