© 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. 8651
    Prev
    Next
    INDEX
    Explanations

    effects, -shaped, undercut, acking, contrast, calotte

    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
     tid
    -0.09
     bitwise
    -0.08
    bu
    -0.08
     ali
    -0.08
    ï¸
    -0.08
    theless
    -0.07
     undert
    -0.07
     adv
    -0.07
     "...
    -0.07
     handshake
    -0.07
    POSITIVE LOGITS
     Provision
    0.10
     Cush
    0.10
     Govern
    0.09
     Pablo
    0.09
    abs
    0.08
     effect
    0.08
     Virgin
    0.08
    -Based
    0.08
    ãģĹãģĭ
    0.08
    æ³ķ
    0.08
    Activations Density 0.831%

    No Known Activations