© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4143
    Prev
    Next
    INDEX
    Explanations

    punctuation and code comments

    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
    _CC
    -0.10
    -0.10
    ión
    -0.10
    owie
    -0.09
    hetto
    -0.09
    plx
    -0.09
     fol
    -0.09
     stil
    -0.09
    hal
    -0.09
    iton
    -0.08
    POSITIVE LOGITS
    uzz
    0.09
    Advertisement
    0.07
    REA
    0.07
    atern
    0.07
    unte
    0.07
    igo
    0.07
     sequentially
    0.07
     fatalities
    0.07
     brig
    0.07
    illac
    0.06
    Activations Density 0.347%

    No Known Activations