© 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. 3445
    Prev
    Next
    INDEX
    Explanations

    closing salutations and sign-offs

    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
    vil
    -0.11
    .chapter
    -0.11
    Invoker
    -0.10
     prefs
    -0.10
    <<<<
    -0.10
    OI
    -0.10
    rss
    -0.10
     Sanctuary
    -0.10
    ioso
    -0.10
     verr
    -0.10
    POSITIVE LOGITS
     enclosed
    0.16
    incerely
    0.14
     Yours
    0.14
     Regards
    0.13
     attached
    0.12
    Dear
    0.12
     Attached
    0.11
     letter
    0.11
     Your
    0.10
     Dear
    0.10
    Activations Density 0.543%

    No Known Activations