© 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. 54131
    Prev
    Next
    INDEX
    Explanations

    listing items or parts of a list

    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
    er
    -0.11
    ese
    -0.11
    ists
    -0.11
    ly
    -0.11
    ers
    -0.11
    istic
    -0.10
    ed
    -0.10
    INGS
    -0.09
    ings
    -0.09
    bies
    -0.09
    POSITIVE LOGITS
    íģ¬
    0.12
    cular
    0.12
    kins
    0.11
    udy
    0.11
    uml
    0.11
    ioned
    0.11
    uthor
    0.11
    ual
    0.11
    velt
    0.10
    ÑģÑĭ
    0.10
    Activations Density 0.061%

    No Known Activations