© 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. 61579
    Prev
    Next
    INDEX
    Explanations

    numbers followed by period

    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
    <|endoftext|>
    -0.08
    wa
    -0.07
    flash
    -0.07
    forge
    -0.07
    189
    -0.06
     Batter
    -0.06
     '
    -0.06
     nominated
    -0.06
     starred
    -0.06
    IA
    -0.06
    POSITIVE LOGITS
    assin
    0.13
    uci
    0.11
    Powered
    0.11
    .clf
    0.11
    /Instruction
    0.10
    WithOptions
    0.10
    [System
    0.10
    isclosed
    0.10
    -parent
    0.10
     Initiative
    0.10
    Activations Density 0.009%

    No Known Activations