© 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. 322
    Prev
    Next
    INDEX
    Explanations

    traditional methods and approaches

    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
     unusual
    -0.10
     Prefer
    -0.10
     unusually
    -0.08
    prefer
    -0.08
     transcend
    -0.08
     preferably
    -0.08
     specially
    -0.08
     quieter
    -0.08
     aud
    -0.08
     specifically
    -0.08
    POSITIVE LOGITS
     traditional
    0.20
     conventional
    0.16
     Traditional
    0.15
    traditional
    0.15
     traditionally
    0.14
    Traditional
    0.13
     outdated
    0.13
     inefficient
    0.13
     static
    0.12
     reliance
    0.12
    Activations Density 3.047%

    No Known Activations