© 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. 55447
    Prev
    Next
    INDEX
    Explanations

    term followed by definition (refers, encompasses, used)

    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
     adjective
    -0.10
    aca
    -0.08
    _pow
    -0.08
     hur
    -0.07
     synonym
    -0.07
     poss
    -0.07
    istically
    -0.07
     alta
    -0.07
     acquire
    -0.07
    è¶
    -0.07
    POSITIVE LOGITS
     timings
    0.11
    BU
    0.10
    ernes
    0.10
    leans
    0.09
    .Rem
    0.09
    ınd
    0.09
    .pass
    0.09
     Sweep
    0.09
    odate
    0.09
    dana
    0.09
    Activations Density 0.044%

    No Known Activations