© 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. 645
    Prev
    Next
    INDEX
    Explanations

    W, Wa, Wan, Wak, x, ol

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to single-letter tokens (especially "w" and "x") and words/tokens that begin with those letters.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    western
    -0.11
     wards
    -0.10
    wave
    -0.10
    _wave
    -0.10
    ant
    -0.10
     wound
    -0.09
    aux
    -0.09
    Highest
    -0.09
    writers
    -0.09
    WE
    -0.09
    POSITIVE LOGITS
    robe
    0.13
    nesday
    0.12
    obble
    0.11
     Fargo
    0.10
    ì¹ĺ
    0.10
    fully
    0.10
    abouts
    0.10
    ickers
    0.10
    craft
    0.09
    abi
    0.09
    Activations Density 2.216%

    No Known Activations