© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    commas and 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
    amon
    -0.09
     due
    -0.09
    vre
    -0.08
    ecause
    -0.08
     since
    -0.08
     dominating
    -0.08
    immer
    -0.08
     setHidden
    -0.07
    wire
    -0.07
     because
    -0.07
    POSITIVE LOGITS
     therefore
    0.13
     hence
    0.11
    eel
    0.10
    aku
    0.10
     erg
    0.10
    exc
    0.09
     thereby
    0.09
     chill
    0.09
    cur
    0.09
    buffer
    0.08
    Activations Density 0.342%

    No Known Activations