© 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. 682
    Prev
    Next
    INDEX
    Explanations

    relative clauses

    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
    én
    -0.07
     suck
    -0.07
    wk
    -0.07
    ogh
    -0.07
    pher
    -0.07
     (?)
    -0.07
    esp
    -0.06
    edit
    -0.06
    yet
    -0.06
    -but
    -0.06
    POSITIVE LOGITS
     which
    0.28
     whose
    0.25
    which
    0.24
    whose
    0.21
     WHICH
    0.19
     коÑĤоÑĢ
    0.18
     коÑĤоÑĢÑĭй
    0.18
     aka
    0.17
     whom
    0.15
     who
    0.14
    Activations Density 1.538%

    No Known Activations