© 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. 3914
    Prev
    Next
    INDEX
    Explanations

    un- forming negative or contrary concepts

    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
    coded
    -0.10
    c
    -0.10
    packed
    -0.09
    authorized
    -0.09
    orgia
    -0.09
     Deb
    -0.09
    coding
    -0.09
    locking
    -0.09
    buster
    -0.09
    -existent
    -0.09
    POSITIVE LOGITS
    ification
    0.12
    nn
    0.10
    uce
    0.10
    ifying
    0.10
    ivariate
    0.10
    icity
    0.09
     decre
    0.09
    ites
    0.09
    idade
    0.09
    ese
    0.09
    Activations Density 0.057%

    No Known Activations