© 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. 2218
    Prev
    Next
    INDEX
    Explanations

    pointer dereference and increment

    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
     stick
    -0.09
    tha
    -0.08
    ynch
    -0.08
    egov
    -0.08
     ups
    -0.08
     carriage
    -0.08
    éc
    -0.08
    wc
    -0.08
     Wake
    -0.08
    aser
    -0.08
    POSITIVE LOGITS
    itre
    0.10
    shire
    0.09
     Lan
    0.09
    quat
    0.09
    lap
    0.08
    CHAIN
    0.08
    ansion
    0.08
    uur
    0.08
    yre
    0.08
    ype
    0.08
    Activations Density 0.030%

    No Known Activations