© 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. 61555
    Prev
    Next
    INDEX
    Explanations

    underlying the

    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
    RAW
    -0.11
     RAW
    -0.10
     Porto
    -0.09
    ppy
    -0.09
     outr
    -0.09
     Jarvis
    -0.09
    ibel
    -0.09
    ippo
    -0.09
     organising
    -0.09
    thers
    -0.08
    POSITIVE LOGITS
    elden
    0.08
     self
    0.07
    back
    0.07
     Pat
    0.07
    ady
    0.07
    cn
    0.07
    indi
    0.07
    ò
    0.07
    irth
    0.07
     mor
    0.07
    Activations Density 0.001%

    No Known Activations