© 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. 3139
    Prev
    Next
    INDEX
    Explanations

    biographies of individuals and their life details

    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
    lish
    -0.08
     jar
    -0.08
    aret
    -0.08
    åıĭ
    -0.07
     Original
    -0.07
    enco
    -0.07
     sei
    -0.07
     teammate
    -0.07
     saturated
    -0.07
     Uns
    -0.07
    POSITIVE LOGITS
    Joined
    0.12
     hobbies
    0.12
     backgrounds
    0.12
     Joined
    0.11
     Experience
    0.11
     qualifications
    0.10
     background
    0.10
     Born
    0.10
     experience
    0.10
     Passion
    0.10
    Activations Density 0.650%

    No Known Activations