© 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. 54812
    Prev
    Next
    INDEX
    Explanations

    hexadecimal digits and strings

    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
    icket
    -0.10
     propri
    -0.10
     BLE
    -0.10
    quent
    -0.10
    eor
    -0.10
    eo
    -0.10
     Masc
    -0.10
     Prometheus
    -0.10
     mash
    -0.09
    gan
    -0.09
    POSITIVE LOGITS
    .dc
    0.08
    .svg
    0.08
     Butter
    0.07
     GS
    0.07
    gard
    0.07
     Nug
    0.06
    ally
    0.06
    aph
    0.06
    tras
    0.06
     Alternate
    0.06
    Activations Density 0.001%

    No Known Activations