© 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. 54268
    Prev
    Next
    INDEX
    Explanations

    Slashdot or slash endpoint

    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
    bk
    -0.10
     Places
    -0.09
    ะ
    -0.09
    etz
    -0.09
    ++++
    -0.08
    tx
    -0.08
    stead
    -0.08
     [@
    -0.08
    blem
    -0.08
    age
    -0.08
    POSITIVE LOGITS
    (es
    0.11
    ers
    0.09
    ki
    0.09
    -minded
    0.09
    dot
    0.08
    'es
    0.08
    .oc
    0.08
    aph
    0.08
    ymm
    0.08
    por
    0.08
    Activations Density 0.002%

    No Known Activations