© 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. 58495
    Prev
    Next
    INDEX
    Explanations

    word suffixes indicating properties or states

    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
    oom
    -0.09
    -looking
    -0.09
     (“
    -0.08
    car
    -0.08
     enough
    -0.08
    ingly
    -0.08
    ably
    -0.07
    /dist
    -0.07
    -sized
    -0.07
    g
    -0.07
    POSITIVE LOGITS
    intern
    0.11
     мÑĭ
    0.11
    usz
    0.10
    tout
    0.10
    ajs
    0.10
    Broker
    0.09
    lea
    0.09
    QQ
    0.09
     Mans
    0.09
    rox
    0.09
    Activations Density 0.099%

    No Known Activations