© 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. 57329
    Prev
    Next
    INDEX
    Explanations

    special name A

    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
    ANI
    -0.08
    Shadow
    -0.08
    ambient
    -0.08
     Jou
    -0.07
     deducted
    -0.07
     Fol
    -0.07
     Dalton
    -0.07
    Cooldown
    -0.07
    ADOW
    -0.07
    herits
    -0.07
    POSITIVE LOGITS
    mps
    0.09
    los
    0.08
    ido
    0.08
     Acres
    0.08
     Dawson
    0.08
    lf
    0.08
     Boards
    0.08
    904
    0.08
     boards
    0.08
     Hansen
    0.08
    Activations Density 0.054%

    No Known Activations