© 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. 57608
    Prev
    Next
    INDEX
    Explanations

    conventional wisdom and teaching

    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
    ermann
    -0.11
    abs
    -0.09
    cheid
    -0.09
    SQLException
    -0.09
    .nd
    -0.09
    iglia
    -0.09
    +(\
    -0.09
    ÑĢаÐ
    -0.08
     attention
    -0.08
     fuzz
    -0.08
    POSITIVE LOGITS
     aver
    0.09
     believed
    0.09
    odoxy
    0.08
    olders
    0.08
     subscribed
    0.08
     beliefs
    0.08
     steady
    0.08
     lin
    0.07
     prevailing
    0.07
     influences
    0.07
    Activations Density 0.100%

    No Known Activations