© 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. 3413
    Prev
    Next
    INDEX
    Explanations

    designed specifically for a purpose

    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
    pest
    -0.08
     Nil
    -0.08
    isco
    -0.08
     POV
    -0.08
     stil
    -0.08
     Forced
    -0.08
    punk
    -0.08
    urable
    -0.08
     chez
    -0.08
    项
    -0.08
    POSITIVE LOGITS
     specifically
    0.18
     designed
    0.16
     purpose
    0.14
    Designed
    0.14
     expressly
    0.14
     Designed
    0.13
     deliberately
    0.13
     purposely
    0.12
     ÑĩÑĤобÑĭ
    0.12
    purpose
    0.12
    Activations Density 0.313%

    No Known Activations