© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    cause/effect relationship

    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
     undergo
    -0.13
     Uses
    -0.10
     reside
    -0.10
     uses
    -0.10
     abst
    -0.10
     lacks
    -0.10
     operates
    -0.09
     penetr
    -0.09
     freely
    -0.09
     hesitate
    -0.09
    POSITIVE LOGITS
     lead
    0.19
     resulted
    0.18
     result
    0.18
     enable
    0.17
    使
    0.17
     enables
    0.16
     leads
    0.16
     resulting
    0.15
     cause
    0.15
    result
    0.15
    Activations Density 1.728%

    No Known Activations