© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    because, especially, since

    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
     unb
    -0.11
     somehow
    -0.10
     Enough
    -0.10
    adt
    -0.10
     mirac
    -0.09
    usan
    -0.09
    itta
    -0.09
     yay
    -0.09
    ,on
    -0.09
    ysi
    -0.09
    POSITIVE LOGITS
     because
    0.20
    because
    0.15
     especially
    0.14
     Because
    0.13
    especially
    0.13
     unless
    0.12
    Because
    0.12
     Especially
    0.11
     since
    0.11
     porque
    0.11
    Activations Density 0.465%

    No Known Activations