© 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. 57432
    Prev
    Next
    INDEX
    Explanations

    yes, no, yeah affirmation or negation

    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
    иÑĤÑĮ
    -0.10
    cci
    -0.10
     Ih
    -0.09
    /groups
    -0.09
    GMT
    -0.09
    riel
    -0.09
    ð
    -0.09
    pag
    -0.09
     tipped
    -0.09
    yre
    -0.09
    POSITIVE LOGITS
    rust
    0.08
    nick
    0.08
     Ep
    0.07
     Mang
    0.07
    ĽĦ
    0.07
    ROS
    0.07
    kel
    0.07
    /E
    0.07
     sticking
    0.07
    eron
    0.07
    Activations Density 0.042%

    No Known Activations