© 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. 3921
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
     rightful
    -0.08
    ures
    -0.08
     mag
    -0.08
    oct
    -0.08
    ire
    -0.08
    ires
    -0.07
     Ach
    -0.07
    rikes
    -0.07
    docs
    -0.07
    opr
    -0.07
    POSITIVE LOGITS
    agra
    0.09
    boa
    0.09
    agos
    0.09
    SED
    0.09
    ft
    0.09
    alone
    0.09
    UIL
    0.09
    <|fim_middle|>
    0.09
    ada
    0.09
    aj
    0.08
    Activations Density 0.752%

    No Known Activations