© 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. 4605
    Prev
    Next
    INDEX
    Explanations

    sentence terminators followed by 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
     prol
    -0.09
     BUT
    -0.09
     HOWEVER
    -0.09
     however
    -0.08
     because
    -0.08
     thus
    -0.08
    wig
    -0.08
     spur
    -0.07
     Mathematic
    -0.07
    ä½Ĩ
    -0.07
    POSITIVE LOGITS
     Ney
    0.10
    aal
    0.09
    ulas
    0.09
     carousel
    0.09
    (nr
    0.09
    auer
    0.09
    MAS
    0.09
     têm
    0.09
     Former
    0.09
    iets
    0.09
    Activations Density 0.139%

    No Known Activations