© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 563
    Prev
    Next
    INDEX
    Explanations

    strong enough / evidence / associated

    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
    оÑģÑĮ
    -0.12
    cer
    -0.10
    .myapplication
    -0.10
    loth
    -0.10
    ORY
    -0.10
    ory
    -0.10
    aptive
    -0.09
    liv
    -0.09
    ogi
    -0.09
     perfor
    -0.09
    POSITIVE LOGITS
    ness
    0.16
     enough
    0.15
    est
    0.15
    ening
    0.15
    holds
    0.15
    ened
    0.14
    (er
    0.13
    /we
    0.13
    ens
    0.11
    ener
    0.11
    Activations Density 1.105%

    No Known Activations