© 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. 2402
    Prev
    Next
    INDEX
    Explanations

    suffix -ive, -ant, -ation, -ity

    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
    ardy
    -0.10
    inem
    -0.10
     enclosing
    -0.09
     Burning
    -0.09
    ocket
    -0.09
     refere
    -0.09
    referer
    -0.09
    landing
    -0.09
     landing
    -0.09
     ï¼
    -0.09
    POSITIVE LOGITS
     ing
    0.07
    Adj
    0.07
    olt
    0.07
     mism
    0.07
     mismatch
    0.07
    им
    0.06
    ocity
    0.06
    erot
    0.06
     tand
    0.06
     stamp
    0.06
    Activations Density 0.280%

    No Known Activations