© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    stieger, stelzer, ste, stee

    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
    stat
    -0.13
    stone
    -0.11
    -0.11
     stain
    -0.11
    rist
    -0.11
    star
    -0.10
     sting
    -0.10
    strict
    -0.10
     unst
    -0.10
     stance
    -0.10
    POSITIVE LOGITS
     quo
    0.15
    holder
    0.13
    holders
    0.13
    igmat
    0.12
    ¤í
    0.12
    coach
    0.11
    igm
    0.10
    ards
    0.10
    hread
    0.10
    rene
    0.10
    Activations Density 1.866%

    No Known Activations