© 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. 3784
    Prev
    Next
    INDEX
    Explanations

    procedure after complications

    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
    irc
    -0.09
     bek
    -0.08
    tex
    -0.08
     tonic
    -0.08
     Charg
    -0.08
    ropa
    -0.08
     swagger
    -0.08
     Fol
    -0.08
    amb
    -0.08
     intim
    -0.08
    POSITIVE LOGITS
    mars
    0.09
    ques
    0.09
    inee
    0.09
    ï¿
    0.09
     tort
    0.09
     eu
    0.09
    verts
    0.09
    uber
    0.09
     NRF
    0.08
    osti
    0.08
    Activations Density 0.009%

    No Known Activations