© 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. 57169
    Prev
    Next
    INDEX
    Explanations

    assignments, conditions, var, assignment, call, func

    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
    labs
    -0.08
    alse
    -0.08
    flu
    -0.08
     brush
    -0.08
    è¦ĭ
    -0.07
    æľ¬
    -0.07
    LD
    -0.07
    wei
    -0.07
     schem
    -0.07
     rehe
    -0.07
    POSITIVE LOGITS
    sto
    0.10
    quier
    0.09
     Farrell
    0.09
     Corm
    0.09
     dun
    0.09
     uniform
    0.09
     setC
    0.09
     ambient
    0.08
     aggrav
    0.08
     nesting
    0.08
    Activations Density 0.117%

    No Known Activations