© 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. 54862
    Prev
    Next
    INDEX
    Explanations

    verb + ing / able / prepositions

    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
    lut
    -0.11
    gue
    -0.10
    ihat
    -0.09
    -enter
    -0.09
    lid
    -0.09
    nost
    -0.08
    argo
    -0.08
    -0.08
    ivate
    -0.08
    fdb
    -0.08
    POSITIVE LOGITS
    ings
    0.15
    ÂŃing
    0.14
    -ing
    0.12
    ingly
    0.11
    [s
    0.10
    swith
    0.10
    able
    0.10
    ING
    0.09
    ing
    0.09
    (s
    0.09
    Activations Density 0.095%

    No Known Activations