© 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. 2854
    Prev
    Next
    INDEX
    Explanations

    connection or function explained

    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
     ims
    -0.12
    /feed
    -0.12
     PTS
    -0.10
     Usually
    -0.10
    ikh
    -0.10
    overe
    -0.09
     vinc
    -0.09
     usually
    -0.09
     Often
    -0.09
     forsk
    -0.09
    POSITIVE LOGITS
     unspecified
    0.16
     allegedly
    0.12
     supposedly
    0.12
     apparently
    0.11
     presumably
    0.11
     reportedly
    0.10
     (?)
    0.10
     "...
    0.09
     rather
    0.09
     suggested
    0.09
    Activations Density 0.153%

    No Known Activations