© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    un- prefix indicating absence or negation

    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
    emean
    -0.09
    иÑĢов
    -0.09
    oust
    -0.09
    ipt
    -0.09
    LLU
    -0.08
    arded
    -0.08
     Pou
    -0.08
    Clock
    -0.08
     sublic
    -0.08
    dden
    -0.08
    POSITIVE LOGITS
    /un
    0.10
    ables
    0.09
    utable
    0.09
    /read
    0.08
    able
    0.08
    Presenter
    0.08
    abeth
    0.08
    á»ijng
    0.08
    ches
    0.08
    orial
    0.07
    Activations Density 0.255%

    No Known Activations