© 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. 2375
    Prev
    Next
    INDEX
    Explanations

    .cpp files and connections

    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
    moz
    -0.10
    vik
    -0.09
    inish
    -0.09
    VENT
    -0.09
    usi
    -0.08
     latin
    -0.08
    mts
    -0.08
    entions
    -0.08
     comp
    -0.08
    /el
    -0.08
    POSITIVE LOGITS
     Jad
    0.09
     banned
    0.08
    è¶ħ
    0.08
     Aad
    0.07
     edge
    0.07
     EDGE
    0.07
     Edge
    0.07
     Bau
    0.07
    iron
    0.07
     surrounding
    0.07
    Activations Density 0.248%

    No Known Activations