© 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. 4040
    Prev
    Next
    INDEX
    Explanations

    reporting speech or writing

    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
     Discussions
    -0.11
     whisper
    -0.11
     discussions
    -0.11
     interviews
    -0.11
     discussion
    -0.10
     voices
    -0.10
     Convenient
    -0.10
    Interview
    -0.10
     discuss
    -0.10
     conversations
    -0.09
    POSITIVE LOGITS
     writing
    0.16
     wrote
    0.16
     written
    0.16
    åĨĻ
    0.13
     write
    0.12
     handwritten
    0.12
    -written
    0.12
     penned
    0.12
     Writing
    0.12
     Written
    0.12
    Activations Density 0.210%

    No Known Activations