© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    people who watch or read

    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
     individuals
    -0.09
     someone
    -0.09
    isd
    -0.08
    rie
    -0.08
    eter
    -0.08
    someone
    -0.08
    Nos
    -0.08
     callable
    -0.08
     charismatic
    -0.08
     Brun
    -0.08
    POSITIVE LOGITS
     audiences
    0.19
     audience
    0.17
     viewers
    0.15
     readers
    0.14
     listeners
    0.13
     Audience
    0.12
     voters
    0.12
     reader
    0.12
     Readers
    0.12
    aud
    0.11
    Activations Density 0.271%

    No Known Activations