© 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. 1839
    Prev
    Next
    INDEX
    Explanations

    when followed by pronoun

    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
     never
    -0.09
    PEC
    -0.08
     swore
    -0.08
    sWith
    -0.08
    ITS
    -0.08
     fig
    -0.08
    xico
    -0.08
    ookie
    -0.08
    İ
    -0.08
    ets
    -0.08
    POSITIVE LOGITS
    /if
    0.34
    soever
    0.24
    EVER
    0.21
    ver
    0.19
     confronted
    0.19
    eve
    0.19
     faced
    0.19
    /how
    0.16
     considering
    0.16
     compared
    0.15
    Activations Density 0.524%

    No Known Activations