© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    how can I do

    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
     burge
    -0.13
     resonate
    -0.12
     recurse
    -0.12
     coincide
    -0.12
     revoke
    -0.12
     expire
    -0.11
     abound
    -0.11
     resend
    -0.11
     withstand
    -0.11
     haunt
    -0.11
    POSITIVE LOGITS
     use
    0.12
     reverse
    0.08
     familiar
    0.08
     physically
    0.08
     USE
    0.08
     Use
    0.08
     design
    0.08
     painstaking
    0.08
     unten
    0.08
     simply
    0.07
    Activations Density 4.001%

    No Known Activations