© 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. 822
    Prev
    Next
    INDEX
    Explanations

    Ryan air, Ryan Mallon

    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
    ing
    -0.12
    sWith
    -0.10
    ateur
    -0.09
    à¹Į
    -0.09
    ning
    -0.09
    far
    -0.09
    ed
    -0.09
    ble
    -0.09
    aq
    -0.08
    ya
    -0.08
    POSITIVE LOGITS
    еÑĢ
    0.12
    thon
    0.10
    ction
    0.09
    ered
    0.09
    fulness
    0.08
    件
    0.08
    ÑģÑĤан
    0.08
    eries
    0.08
    éĽħ
    0.08
    illion
    0.08
    Activations Density 3.959%

    No Known Activations