© 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. 55526
    Prev
    Next
    INDEX
    Explanations

    division, questions, procedures, identifiers

    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
    gorith
    -0.10
     kut
    -0.10
    áº
    -0.10
    KE
    -0.09
    claims
    -0.09
    amps
    -0.09
    dek
    -0.09
    asser
    -0.09
     evolutionary
    -0.09
    Specification
    -0.09
    POSITIVE LOGITS
    hip
    0.10
    s
    0.09
    itting
    0.08
    ny
    0.08
     Sweep
    0.08
    n
    0.08
    ment
    0.08
    na
    0.08
    l
    0.07
     wheel
    0.07
    Activations Density 0.001%

    No Known Activations