© 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. 56235
    Prev
    Next
    INDEX
    Explanations

    ```json{ "explanation": "appellant appeals conviction"}```

    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
     Committees
    -0.10
    beg
    -0.09
    ↵				↵
    -0.09
    /GL
    -0.09
    beth
    -0.09
    inya
    -0.09
     elapsedTime
    -0.09
    /values
    -0.09
    .which
    -0.09
     Nobel
    -0.08
    POSITIVE LOGITS
     fram
    0.08
    opp
    0.08
    fel
    0.08
    "d
    0.07
    imp
    0.07
     Insider
    0.07
    بر
    0.07
    ual
    0.07
    hill
    0.07
     impost
    0.07
    Activations Density 0.001%

    No Known Activations