© 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. 3262
    Prev
    Next
    INDEX
    Explanations

    combining lists or data

    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
    ardown
    -0.10
    HORT
    -0.09
    tica
    -0.09
     simultaneous
    -0.09
    ÑĤеÑĢ
    -0.09
     Brush
    -0.09
    _apps
    -0.09
     multit
    -0.09
     pand
    -0.09
    	setup
    -0.09
    POSITIVE LOGITS
     merging
    0.17
     joining
    0.16
     merge
    0.16
     Join
    0.16
     join
    0.16
     unite
    0.15
     merger
    0.15
    merge
    0.15
     combine
    0.15
     Merge
    0.14
    Activations Density 0.380%

    No Known Activations