© 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. 703
    Prev
    Next
    INDEX
    Explanations

    aggravates, potentiates, implicates

    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
     Hun
    -0.12
    amation
    -0.10
    ropy
    -0.09
    usty
    -0.09
    aker
    -0.09
    horn
    -0.08
    дин
    -0.08
     motion
    -0.08
    kip
    -0.08
    NESS
    -0.08
    POSITIVE LOGITS
    ed
    0.16
    ing
    0.16
    äºĨ
    0.13
    entially
    0.11
    aneously
    0.10
    led
    0.10
    edException
    0.10
    edBy
    0.09
    arily
    0.09
    istically
    0.09
    Activations Density 1.640%

    No Known Activations