© 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. 1690
    Prev
    Next
    INDEX
    Explanations

    of theory into practice

    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
    aret
    -0.08
     suite
    -0.08
    ä¸ĵ
    -0.08
    /bl
    -0.07
    extras
    -0.07
    egin
    -0.07
    inte
    -0.07
    SU
    -0.07
     complimentary
    -0.07
    Sou
    -0.07
    POSITIVE LOGITS
     actual
    0.17
    actual
    0.16
     reality
    0.15
     realities
    0.15
    -real
    0.15
     practical
    0.14
    /pr
    0.14
     Actual
    0.14
     real
    0.14
    Actual
    0.13
    Activations Density 1.980%

    No Known Activations