© 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. 56529
    Prev
    Next
    INDEX
    Explanations

    documentation comments with `@return`

    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
    omid
    -0.11
    aturing
    -0.10
    andes
    -0.10
    .memory
    -0.10
    ì¹ĺ
    -0.10
    arge
    -0.09
    cum
    -0.09
    ange
    -0.09
    crest
    -0.09
    /blue
    -0.09
    POSITIVE LOGITS
     Ezra
    0.08
    <td
    0.08
     Autor
    0.07
    ped
    0.06
     maxx
    0.06
    IAS
    0.06
     Eag
    0.06
     Marr
    0.06
     **/↵↵
    0.06
     Sour
    0.06
    Activations Density 0.003%

    No Known Activations