© 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. 55199
    Prev
    Next
    INDEX
    Explanations

    ability of

    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
    noon
    -0.09
     Fet
    -0.08
    bos
    -0.08
    bild
    -0.08
    avanaugh
    -0.08
     kup
    -0.08
    ifo
    -0.08
    wire
    -0.07
    Sentence
    -0.07
    unct
    -0.07
    POSITIVE LOGITS
    inky
    0.09
     bomber
    0.09
     submar
    0.09
    entes
    0.09
    _hostname
    0.09
     Bair
    0.08
     riff
    0.08
     templ
    0.08
     bait
    0.08
    reek
    0.08
    Activations Density 0.043%

    No Known Activations