© 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. 57506
    Prev
    Next
    INDEX
    Explanations

    just

    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
     simply
    -0.13
     simplement
    -0.10
     notwithstanding
    -0.09
     merely
    -0.09
    mentation
    -0.09
     lanç
    -0.09
    akan
    -0.09
     Ak
    -0.09
    Ak
    -0.09
     nonetheless
    -0.09
    POSITIVE LOGITS
     Mojo
    0.09
    ania
    0.08
    ute
    0.08
    æłĩé¢ĺ
    0.07
    ingles
    0.07
    	use
    0.07
     incl
    0.07
     squeez
    0.07
     antid
    0.07
     rally
    0.07
    Activations Density 0.021%

    No Known Activations