© 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. 1756
    Prev
    Next
    INDEX
    Explanations

    forensic, team, stadium, arrested, important, evaluated

    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
    ffd
    -0.11
    undry
    -0.10
    uttgart
    -0.10
    Tumblr
    -0.10
     ?>↵↵↵
    -0.10
    usterity
    -0.10
     BaseController
    -0.10
    Prostit
    -0.10
     TestUtils
    -0.10
    conde
    -0.10
    POSITIVE LOGITS
     [âĢ¦]↵↵
    0.22
     [âĢ¦
    0.21
     [...]↵↵
    0.20
     ...↵
    0.15
     [...]
    0.14
     ...↵↵
    0.14
    <|fim_suffix|>
    0.14
     [...
    0.14
     [âĢ¦]
    0.13
     (...)
    0.13
    Activations Density 9.035%

    No Known Activations