© 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. 84
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common sentence starts

    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
     âĿ¤
    -0.10
     Unfortunately
    -0.09
    urtle
    -0.08
     appro
    -0.08
    OTE
    -0.08
    ¶
    -0.08
    cerpt
    -0.08
     dynamically
    -0.08
    Unfortunately
    -0.08
    lyn
    -0.08
    POSITIVE LOGITS
     Worse
    0.27
     :(
    0.21
     Fortunately
    0.18
    Fortunately
    0.17
     remedy
    0.17
     worse
    0.17
    Luckily
    0.16
     Luckily
    0.15
     compounded
    0.15
     remed
    0.14
    Activations Density 2.378%

    No Known Activations