© 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. 4382
    Prev
    Next
    INDEX
    Explanations

    placement and interactions

    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
     kut
    -0.12
    quil
    -0.12
    -ts
    -0.11
    /org
    -0.11
    ITA
    -0.10
    kre
    -0.10
    ucher
    -0.10
    adol
    -0.10
    chsel
    -0.10
    eln
    -0.10
    POSITIVE LOGITS
     interacts
    0.12
     penetrate
    0.12
     interacting
    0.12
     penetrating
    0.11
     targeting
    0.10
     Placement
    0.10
     placement
    0.10
    fits
    0.09
     interact
    0.09
     Ready
    0.09
    Activations Density 0.616%

    No Known Activations