© 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. 3952
    Prev
    Next
    INDEX
    Explanations

    referred to as

    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
     called
    -0.09
     compt
    -0.09
     Colt
    -0.08
    yc
    -0.08
     Ec
    -0.08
    called
    -0.08
     Called
    -0.08
    ag
    -0.07
    hoe
    -0.07
    åĪ«
    -0.07
    POSITIVE LOGITS
    -ng
    0.10
    innen
    0.09
    epar
    0.09
     Impl
    0.09
    rst
    0.09
     Prot
    0.09
     tw
    0.09
    amientos
    0.09
    reur
    0.08
    das
    0.08
    Activations Density 0.091%

    No Known Activations