© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56126
    Prev
    Next
    INDEX
    Explanations

    explains or explains a result

    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
    eti
    -0.10
    adas
    -0.09
     homogeneous
    -0.08
     slim
    -0.08
     fasc
    -0.08
    ethod
    -0.08
    .Alignment
    -0.07
    ITH
    -0.07
    inte
    -0.07
     sal
    -0.07
    POSITIVE LOGITS
     explain
    0.10
     Blade
    0.10
     Explain
    0.10
     explaining
    0.09
     explains
    0.09
     unsuccessfully
    0.09
     mime
    0.09
     explanation
    0.09
     Explanation
    0.09
    (#
    0.09
    Activations Density 0.118%

    No Known Activations