© 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. 4115
    Prev
    Next
    INDEX
    Explanations

    actions completed or triggered

    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
     Kore
    -0.10
     transition
    -0.09
     Mash
    -0.08
    izen
    -0.08
    boom
    -0.08
    å¹
    -0.08
    �s
    -0.07
     Transition
    -0.07
    izio
    -0.07
     taper
    -0.07
    POSITIVE LOGITS
    enton
    0.10
    viso
    0.09
    /is
    0.09
    ij
    0.09
    ÑĪе
    0.09
    iners
    0.09
    dep
    0.08
    mers
    0.08
    recht
    0.08
    sav
    0.08
    Activations Density 0.355%

    No Known Activations