© 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. 54135
    Prev
    Next
    INDEX
    Explanations

    mathematical terms

    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
     bay
    -0.10
    irst
    -0.09
    cplusplus
    -0.08
    ynn
    -0.08
     Winston
    -0.08
    rippling
    -0.07
    collections
    -0.07
    /github
    -0.07
     Tmin
    -0.07
    ONS
    -0.07
    POSITIVE LOGITS
     sec
    0.09
    aud
    0.09
     aud
    0.09
     vinc
    0.09
    ilde
    0.09
    /services
    0.08
     Vanguard
    0.08
    iates
    0.08
    ummings
    0.08
     recognizer
    0.08
    Activations Density 0.021%

    No Known Activations