© 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. 57747
    Prev
    Next
    INDEX
    Explanations

    Can you succeed

    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
    angen
    -0.10
    elles
    -0.09
    active
    -0.08
     Viv
    -0.08
    -active
    -0.08
    legg
    -0.08
     Want
    -0.08
     Poss
    -0.07
     actively
    -0.07
    ange
    -0.07
    POSITIVE LOGITS
     Enough
    0.12
     correctly
    0.11
     Incoming
    0.11
     enough
    0.10
     outweigh
    0.10
     moot
    0.09
     Emer
    0.09
     withstand
    0.09
    hya
    0.09
    usb
    0.09
    Activations Density 0.068%

    No Known Activations