© 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. 54590
    Prev
    Next
    INDEX
    Explanations

    expressing personal feelings and experiences

    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
    za
    -0.09
     disciplined
    -0.08
    sq
    -0.08
    occupation
    -0.08
     occupation
    -0.08
     Zag
    -0.08
    sembled
    -0.07
     Hancock
    -0.07
    ground
    -0.07
    hy
    -0.07
    POSITIVE LOGITS
    -expression
    0.12
     transmitting
    0.11
     vulnerability
    0.11
     communicating
    0.11
     vulner
    0.10
     transmit
    0.10
     televis
    0.10
     expressive
    0.10
    lest
    0.10
     communicator
    0.10
    Activations Density 0.056%

    No Known Activations