© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    disclaimers and licenses without warranty

    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
     ust
    -0.11
    amel
    -0.10
    CLUDING
    -0.10
    subtotal
    -0.10
    apel
    -0.09
     ê
    -0.09
     conf
    -0.09
    passport
    -0.09
    egr
    -0.09
    atin
    -0.09
    POSITIVE LOGITS
    vos
    0.07
    ï
    0.06
    yen
    0.06
    Maker
    0.06
    omatic
    0.06
    оÑģ
    0.06
     Newman
    0.06
    breaker
    0.06
     Boxing
    0.06
    ella
    0.06
    Activations Density 2.702%

    No Known Activations