© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2824
    Prev
    Next
    INDEX
    Explanations

    list structure `(`

    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
     "`
    -0.10
    ulle
    -0.10
    compare
    -0.09
     locales
    -0.09
     [`
    -0.09
     *"
    -0.08
    nen
    -0.08
     _
    -0.08
     TypeScript
    -0.08
    dv
    -0.08
    POSITIVE LOGITS
     Arm
    0.09
    wich
    0.09
    /=
    0.09
     atleast
    0.09
     Arms
    0.09
    -el
    0.08
     Mention
    0.08
    uses
    0.08
     plat
    0.08
    PTH
    0.08
    Activations Density 0.374%

    No Known Activations