© 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. 641
    Prev
    Next
    INDEX
    Explanations

    sound, hearing, and listening

    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
    Ŀ
    -0.09
     lingu
    -0.08
    ilda
    -0.08
    cion
    -0.07
     Presented
    -0.07
     mist
    -0.07
     motion
    -0.07
    ions
    -0.07
    ory
    -0.07
     Mes
    -0.07
    POSITIVE LOGITS
     loudly
    0.15
     louder
    0.15
    visual
    0.14
    /watch
    0.14
     loud
    0.14
    /text
    0.14
    /video
    0.13
    speaker
    0.13
    /music
    0.12
     voices
    0.12
    Activations Density 1.474%

    No Known Activations