© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4133
    Prev
    Next
    INDEX
    Explanations

    similar to another

    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
    ķ
    -0.08
     Francis
    -0.08
    ahun
    -0.07
     ?????
    -0.07
    .constructor
    -0.07
    laus
    -0.07
    isti
    -0.07
     Rubin
    -0.07
    ien
    -0.07
     ??
    -0.07
    POSITIVE LOGITS
     analogous
    0.39
     equivalent
    0.39
     akin
    0.36
     comparable
    0.32
     Equivalent
    0.31
     equivalents
    0.31
     analogue
    0.29
     similar
    0.28
     analog
    0.26
    Equivalent
    0.26
    Activations Density 0.569%

    No Known Activations