© 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. 55670
    Prev
    Next
    INDEX
    Explanations

    Water

    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
    unts
    -0.10
    unt
    -0.09
    tv
    -0.08
    Trace
    -0.08
    reas
    -0.08
    phan
    -0.08
    073
    -0.08
    stag
    -0.08
    Tip
    -0.08
    inho
    -0.08
    POSITIVE LOGITS
    gend
    0.09
     nad
    0.08
    ):-
    0.08
    UNS
    0.08
     Bars
    0.07
    */
    0.07
     perpetual
    0.07
    elfast
    0.07
     tur
    0.07
    HAVE
    0.07
    Activations Density 0.028%

    No Known Activations