© 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. 1841
    Prev
    Next
    INDEX
    Explanations

    overall quality and prevalence

    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
     wegen
    -0.12
     bevor
    -0.12
     preferably
    -0.11
     separately
    -0.11
    	using
    -0.10
     Prefer
    -0.10
     principally
    -0.10
    @student
    -0.10
    blick
    -0.10
    maal
    -0.09
    POSITIVE LOGITS
     indirectly
    0.14
     overall
    0.13
     otherwise
    0.13
     future
    0.13
     tremendously
    0.12
     unnecessarily
    0.12
     eventual
    0.12
     valuable
    0.12
     quicker
    0.11
     effectively
    0.11
    Activations Density 2.982%

    No Known Activations