© 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. 2684
    Prev
    Next
    INDEX
    Explanations

    sending data, developing software, collecting boarding, finding answers, scheduling lessons

    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
    jian
    -0.09
    lico
    -0.08
    itu
    -0.07
     Inserts
    -0.07
    (ph
    -0.07
     Against
    -0.07
     against
    -0.07
    -live
    -0.07
    hil
    -0.07
     autof
    -0.07
    POSITIVE LOGITS
    andom
    0.10
    Big
    0.09
    /releases
    0.09
    nemonic
    0.09
    IW
    0.09
    oren
    0.09
    rink
    0.09
     Saga
    0.09
    Saga
    0.09
    è¶
    0.09
    Activations Density 0.547%

    No Known Activations