© 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. 57267
    Prev
    Next
    INDEX
    Explanations

    zero for

    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
     ret
    -0.10
    enic
    -0.09
    itial
    -0.09
    aux
    -0.09
     fer
    -0.09
     diy
    -0.09
    illi
    -0.08
    PCR
    -0.08
     pinch
    -0.08
    äº
    -0.08
    POSITIVE LOGITS
     Alive
    0.09
    ISIBLE
    0.08
     Aust
    0.08
     leash
    0.08
     Dynam
    0.07
    iston
    0.07
     Null
    0.07
     NULL
    0.07
     Passive
    0.07
    Getty
    0.07
    Activations Density 0.001%

    No Known Activations