© 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. 2852
    Prev
    Next
    INDEX
    Explanations

    old words, archaic language, archaic speech

    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
     HI
    -0.08
    ÑĢ
    -0.08
    ije
    -0.08
     KO
    -0.08
    ,get
    -0.07
    -ish
    -0.07
     tough
    -0.07
     Huff
    -0.07
    PH
    -0.07
    atically
    -0.07
    POSITIVE LOGITS
     unto
    0.22
     shall
    0.13
     thy
    0.13
     hath
    0.13
    unto
    0.13
     counsel
    0.12
     Shall
    0.12
     thee
    0.12
     wherein
    0.11
     mighty
    0.11
    Activations Density 0.532%

    No Known Activations