© 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. 54957
    Prev
    Next
    INDEX
    Explanations

    its or their comparative

    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
     formerly
    -0.10
    æļ
    -0.09
     redistribution
    -0.09
     fick
    -0.08
     cla
    -0.08
    nb
    -0.08
    iki
    -0.08
     Mandatory
    -0.08
    ona
    -0.08
     habit
    -0.08
    POSITIVE LOGITS
    compet
    0.08
     thumbs
    0.08
     Nie
    0.08
    ichten
    0.08
    anal
    0.08
    ypes
    0.08
     predecessors
    0.08
     Cousins
    0.07
    #=
    0.07
    izable
    0.07
    Activations Density 0.023%

    No Known Activations