© 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. 54943
    Prev
    Next
    INDEX
    Explanations

    quotation marks or speech starts

    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
     Dane
    -0.08
    elon
    -0.08
     cam
    -0.08
     explicit
    -0.08
     Cam
    -0.08
     Camp
    -0.08
    edin
    -0.07
    (NS
    -0.07
     []).
    -0.07
     gotta
    -0.07
    POSITIVE LOGITS
    fare
    0.11
    uxe
    0.10
     yes
    0.10
    onas
    0.10
     Yes
    0.10
     Depends
    0.10
    Roger
    0.09
    utto
    0.09
     amen
    0.09
     fare
    0.09
    Activations Density 0.064%

    No Known Activations