© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    as [adverb/quantifier]

    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
    /wait
    -0.10
     tem
    -0.10
    afen
    -0.10
     ValueType
    -0.10
    cola
    -0.10
    ovel
    -0.09
    deo
    -0.09
    ureau
    -0.09
     Regents
    -0.09
    Ĺ
    -0.09
    POSITIVE LOGITS
     as
    0.13
     quanto
    0.13
     mogelijk
    0.11
     wie
    0.10
     possible
    0.09
     Iss
    0.08
    ichi
    0.07
     imaginable
    0.07
     posible
    0.07
    (ref
    0.07
    Activations Density 0.098%

    No Known Activations