© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56670
    Prev
    Next
    INDEX
    Explanations

    as / like, with pronouns

    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
    obel
    -0.11
     IDX
    -0.10
    olg
    -0.10
     Dek
    -0.10
    iga
    -0.09
     traf
    -0.09
    .↵↵↵↵↵↵↵↵↵↵
    -0.09
    iku
    -0.09
    sty
    -0.09
    Dept
    -0.09
    POSITIVE LOGITS
     as
    0.16
     jako
    0.11
     als
    0.11
     sebagai
    0.10
     comme
    0.08
    为
    0.08
     unfavor
    0.08
     como
    0.08
     Say
    0.08
    ken
    0.07
    Activations Density 0.068%

    No Known Activations