© 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. 1167
    Prev
    Next
    INDEX
    Explanations

    Forwarded by

    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
     Lon
    -0.10
    —as
    -0.09
    âĶĢâĶĢâĶĢâĶĢ
    -0.09
    ovsky
    -0.09
    —to
    -0.09
    —you
    -0.08
    cept
    -0.08
    (Display
    -0.08
    umba
    -0.08
    è¨Ģ
    -0.08
    POSITIVE LOGITS
    _.
    0.12
    -.
    0.12
    +↵
    0.10
    ->
    0.09
    atr
    0.09
    esso
    0.09
    s
    0.08
    (
    0.08
    aur
    0.08
    .Stop
    0.08
    Activations Density 0.608%

    No Known Activations