© 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. 55189
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     example
    -0.10
    -example
    -0.10
    rys
    -0.10
    aniu
    -0.10
    otto
    -0.10
    example
    -0.10
    .iterator
    -0.09
     aun
    -0.09
     Example
    -0.09
     Gaines
    -0.09
    POSITIVE LOGITS
     mostly
    0.09
     det
    0.09
     inst
    0.08
     wre
    0.08
     principals
    0.08
     pos
    0.08
    asy
    0.08
     paras
    0.08
     Mostly
    0.08
     stom
    0.07
    Activations Density 0.039%

    No Known Activations