© 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. 667
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     (>
    -0.10
    ITA
    -0.10
    elon
    -0.09
    bulk
    -0.09
    ichi
    -0.09
     Wich
    -0.09
    ammer
    -0.09
    inis
    -0.09
     ware
    -0.09
    amma
    -0.09
    POSITIVE LOGITS
     Tristan
    0.09
    flow
    0.08
     (.
    0.08
    raise
    0.08
    linger
    0.08
     raising
    0.08
     popping
    0.08
     Criterion
    0.07
     pops
    0.07
     flare
    0.07
    Activations Density 1.103%

    No Known Activations