© 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. 58498
    Prev
    Next
    INDEX
    Explanations

    free trial or sample

    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
    yre
    -0.08
    esch
    -0.08
    inform
    -0.07
    ìĥ
    -0.07
     infer
    -0.07
     informal
    -0.07
     prototype
    -0.06
     prelim
    -0.06
     sond
    -0.06
     preliminary
    -0.06
    POSITIVE LOGITS
    igor
    0.10
    sha
    0.10
    usan
    0.09
    asper
    0.09
    iver
    0.09
    obel
    0.09
    æľŁ
    0.09
    -ok
    0.09
    efault
    0.09
    aved
    0.09
    Activations Density 0.011%

    No Known Activations