© 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. 57336
    Prev
    Next
    INDEX
    Explanations

    default values

    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
     orders
    -0.09
    wald
    -0.08
     categorized
    -0.08
    xm
    -0.08
    oria
    -0.08
    orders
    -0.08
    anton
    -0.08
    ivet
    -0.08
     categor
    -0.08
     spender
    -0.08
    POSITIVE LOGITS
     default
    0.19
     defaults
    0.19
    defaults
    0.19
     Defaults
    0.18
    default
    0.18
    ï¼Įé»ĺ认
    0.18
     Default
    0.16
    (default
    0.16
    Default
    0.15
    é»ĺ认
    0.15
    Activations Density 0.137%

    No Known Activations