© 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. 57628
    Prev
    Next
    INDEX
    Explanations

    special characters before code keywords

    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
    mil
    -0.09
    pour
    -0.09
    Ķ
    -0.08
     blogger
    -0.08
    ¾
    -0.08
    hm
    -0.08
     Sab
    -0.08
     Sud
    -0.08
     vista
    -0.08
    VEN
    -0.08
    POSITIVE LOGITS
    arine
    0.08
    	endif
    0.08
    allen
    0.08
    ially
    0.08
    agen
    0.08
     lob
    0.08
    ($)
    0.07
    oses
    0.07
    Ñħ
    0.07
    ainless
    0.07
    Activations Density 0.028%

    No Known Activations