© 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. 8611
    Prev
    Next
    INDEX
    Explanations

    conference honorable mention

    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
    aus
    -0.11
    Č↵
    -0.11
    "]->
    -0.10
    oles
    -0.10
    alloca
    -0.09
    OWER
    -0.09
     )->
    -0.09
    ']->
    -0.09
     Pref
    -0.09
    ANK
    -0.09
    POSITIVE LOGITS
    kers
    0.07
     moment
    0.07
    {return
    0.07
     Alv
    0.07
    iker
    0.07
    ida
    0.07
    cam
    0.07
     unreal
    0.07
    lear
    0.07
    am
    0.07
    Activations Density 0.530%

    No Known Activations