© 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. 56349
    Prev
    Next
    INDEX
    Explanations

    silver followed by place, age, or material

    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
    smith
    -0.10
    vetica
    -0.10
    iew
    -0.09
    vu
    -0.09
    work
    -0.09
     Profession
    -0.09
    ached
    -0.09
    sert
    -0.09
    lay
    -0.09
    lib
    -0.09
    POSITIVE LOGITS
    ed
    0.12
    e
    0.11
    eer
    0.10
    eon
    0.10
    ingly
    0.10
    ia
    0.09
    ing
    0.09
    aire
    0.08
    a
    0.08
    度
    0.08
    Activations Density 0.005%

    No Known Activations