© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55025
    Prev
    Next
    INDEX
    Explanations

    draw, drawing, and graphics

    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
    oria
    -0.13
    oid
    -0.11
    oids
    -0.11
    {\"
    -0.10
     drawing
    -0.10
    eth
    -0.10
    onta
    -0.10
    sa
    -0.10
    ilit
    -0.10
     ballo
    -0.09
    POSITIVE LOGITS
    ick
    0.09
    ian
    0.09
    hf
    0.07
    elf
    0.07
     Obs
    0.07
    line
    0.07
     Slut
    0.07
     essentially
    0.07
    backs
    0.07
     Hosp
    0.06
    Activations Density 0.012%

    No Known Activations