© 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. 61701
    Prev
    Next
    INDEX
    Explanations

    offering support or help

    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
     Friendly
    -0.09
    buch
    -0.09
     Superior
    -0.08
    |h
    -0.08
     Te
    -0.08
     enthusiastically
    -0.08
     Gian
    -0.08
     sponsorship
    -0.08
     sponsoring
    -0.08
    abbr
    -0.08
    POSITIVE LOGITS
    ÑĮ
    0.10
    缮
    0.09
    icy
    0.09
    ENS
    0.09
     diversion
    0.08
    Tr
    0.08
     Chap
    0.08
     hub
    0.08
     Cout
    0.08
     ens
    0.08
    Activations Density 0.033%

    No Known Activations