© 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. 8446
    Prev
    Next
    INDEX
    Explanations

    shoot or shot

    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
    fp
    -0.08
    .setOn
    -0.08
     butcher
    -0.08
     crunch
    -0.08
     bulld
    -0.08
    .sep
    -0.08
    DITION
    -0.08
    okin
    -0.08
    ennen
    -0.08
    ÑģÑĭ
    -0.08
    POSITIVE LOGITS
    guns
    0.13
     fired
    0.13
     disp
    0.10
     vol
    0.10
    linger
    0.09
     Fired
    0.09
    ting
    0.09
    tery
    0.09
    anje
    0.09
     Moz
    0.09
    Activations Density 0.182%

    No Known Activations