© 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. 54183
    Prev
    Next
    INDEX
    Explanations

    comments, code, 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
    ZA
    -0.11
    idge
    -0.10
    za
    -0.10
    ager
    -0.10
     Cly
    -0.09
    oner
    -0.09
    Longrightarrow
    -0.09
    itus
    -0.09
    Manifest
    -0.09
    æĴŃ
    -0.09
    POSITIVE LOGITS
     incl
    0.07
     tense
    0.07
    irst
    0.07
     shopping
    0.07
    olv
    0.07
     hollow
    0.07
     guid
    0.06
    yro
    0.06
     Peace
    0.06
     Prel
    0.06
    Activations Density 0.082%

    No Known Activations