© 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. 55468
    Prev
    Next
    INDEX
    Explanations

    plays a role

    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
    yr
    -0.08
     playing
    -0.08
    -playing
    -0.08
    oa
    -0.08
     inventory
    -0.08
     Occupation
    -0.07
    cube
    -0.07
     Pieces
    -0.07
    ema
    -0.07
     consoles
    -0.07
    POSITIVE LOGITS
    utto
    0.10
    orts
    0.10
    kee
    0.10
    -holder
    0.10
    ione
    0.10
    ilestone
    0.09
     FU
    0.09
    vision
    0.09
    andi
    0.09
    anding
    0.09
    Activations Density 0.011%

    No Known Activations