© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    would

    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
     -->
    -0.09
     --
    -0.08
    Ìģ
    -0.07
     ->
    -0.07
    ::
    -0.07
    ewise
    -0.07
    es
    -0.07
    worthy
    -0.07
     ens
    -0.07
     Jess
    -0.06
    POSITIVE LOGITS
    aison
    0.10
    @student
    0.10
    ARC
    0.10
     Binder
    0.10
    ellt
    0.10
    ADV
    0.10
    oose
    0.09
     ={↵
    0.09
    lsa
    0.09
     ';↵↵
    0.09
    Activations Density 0.195%

    No Known Activations