© 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. 3679
    Prev
    Next
    INDEX
    Explanations

    programming languages and code blocks

    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
    dden
    -0.11
     Inbox
    -0.10
    idas
    -0.09
    icides
    -0.09
     fanc
    -0.09
    ANNOT
    -0.09
     Howell
    -0.09
     penet
    -0.09
    atem
    -0.09
     ride
    -0.09
    POSITIVE LOGITS
     }↵↵↵↵↵↵
    0.09
    `↵
    0.08
    ç¦
    0.08
    uku
    0.08
    ombo
    0.08
    ukan
    0.08
    eor
    0.08
     Clair
    0.07
     ban
    0.07
     Lit
    0.07
    Activations Density 0.062%

    No Known Activations