© 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. 61625
    Prev
    Next
    INDEX
    Explanations

    syntax error: expected

    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
    erno
    -0.11
    istik
    -0.10
     interfer
    -0.09
    _Il
    -0.09
     offic
    -0.09
    AWN
    -0.09
    ä¿®
    -0.09
     refere
    -0.09
    aben
    -0.09
    obby
    -0.08
    POSITIVE LOGITS
     Blair
    0.10
    eds
    0.08
    gon
    0.08
    led
    0.08
     instead
    0.08
     jot
    0.07
    all
    0.07
     brave
    0.07
    ORY
    0.07
    	store
    0.07
    Activations Density 0.012%

    No Known Activations