© 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. 2383
    Prev
    Next
    INDEX
    Explanations

    a mission or passion

    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
     cons
    -0.08
    iment
    -0.08
     tubes
    -0.08
     yourselves
    -0.08
     [[]
    -0.08
     tube
    -0.07
    cling
    -0.07
    getattr
    -0.07
    ember
    -0.07
     Blind
    -0.07
    POSITIVE LOGITS
     philanth
    0.13
     spreading
    0.12
     impart
    0.12
     brid
    0.11
     chall
    0.11
     sharing
    0.10
     global
    0.10
     worldwide
    0.10
     Sharing
    0.10
     entreprene
    0.10
    Activations Density 0.313%

    No Known Activations