© 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. 56399
    Prev
    Next
    INDEX
    Explanations

    variable assignments

    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
    Âł
    -0.09
    otta
    -0.08
     cha
    -0.08
     crunch
    -0.07
    olo
    -0.07
     Kun
    -0.07
     jug
    -0.07
    jug
    -0.07
     Crunch
    -0.07
    unge
    -0.07
    POSITIVE LOGITS
     (!((
    0.11
    resco
    0.10
     Brew
    0.10
    efe
    0.10
    omap
    0.09
    ↵        ↵        ↵
    0.09
     Homepage
    0.09
    ele
    0.09
     Iso
    0.09
    umpt
    0.09
    Activations Density 0.036%

    No Known Activations