© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1332
    Prev
    Next
    INDEX
    Explanations

    uint types

    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
    Negative Logits
    ).↵↵↵↵
    -0.13
    wend
    -0.12
    ].[
    -0.11
    ,âĢ¦↵↵
    -0.11
    ...'↵
    -0.11
    .Rendering
    -0.10
    jom
    -0.10
    '↵↵↵↵
    -0.10
    .@
    -0.10
    afil
    -0.10
    POSITIVE LOGITS
     itself
    0.08
    -Headers
    0.07
    '_
    0.07
    [^
    0.06
     Eh
    0.06
     isn
    0.06
     imm
    0.06
     cram
    0.06
     Ain
    0.06
     _
    0.05
    Activations Density 1.764%

    No Known Activations