© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56090
    Prev
    Next
    INDEX
    Explanations

    methods and approaches

    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
    vor
    -0.08
     barrel
    -0.08
     specificity
    -0.08
    Beth
    -0.07
    åľ°
    -0.07
    bak
    -0.07
     Inf
    -0.07
     bis
    -0.07
     uns
    -0.07
     mash
    -0.07
    POSITIVE LOGITS
    ä¸įåŃĺåľ¨
    0.09
    drawer
    0.09
    ений
    0.09
    лем
    0.09
    ãĥĶ
    0.09
    ikal
    0.09
    jab
    0.09
    acci
    0.09
     :";↵
    0.08
     Chain
    0.08
    Activations Density 0.173%

    No Known Activations