© 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. 2767
    Prev
    Next
    INDEX
    Explanations

    names and titles (Jr, Hin, hitch, Whitespace, hin, ç©, utar, jr, OLL, CTL)

    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
     stud
    -0.11
     Howe
    -0.10
    oren
    -0.10
     McCabe
    -0.10
     fal
    -0.09
     Brooklyn
    -0.09
     Michaels
    -0.09
    mans
    -0.09
     ’
    -0.09
     Stein
    -0.09
    POSITIVE LOGITS
     Jr
    0.10
     Hin
    0.08
     hitch
    0.08
    Whitespace
    0.08
     hin
    0.08
    ç©
    0.08
    utar
    0.07
    jr
    0.07
    OLL
    0.07
    CTL
    0.07
    Activations Density 0.258%

    No Known Activations