© 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. 4367
    Prev
    Next
    INDEX
    Explanations

    whom and him

    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
    ий
    -0.08
    ypad
    -0.08
    ARD
    -0.08
     ));↵↵
    -0.08
     units
    -0.07
     scheme
    -0.07
     compliant
    -0.07
    iew
    -0.07
    Pad
    -0.07
     cooper
    -0.07
    POSITIVE LOGITS
    soever
    0.13
     можно
    0.10
     echo
    0.09
    undy
    0.09
    nah
    0.09
    st
    0.09
    bjerg
    0.09
    oko
    0.08
    lt
    0.08
    agrant
    0.08
    Activations Density 0.095%

    No Known Activations