© 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. 8466
    Prev
    Next
    INDEX
    Explanations

    documentation tags like @param

    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
     describes
    -0.10
     summarizes
    -0.09
    auf
    -0.09
    qua
    -0.09
    athers
    -0.09
     describing
    -0.09
    ена
    -0.09
    ury
    -0.08
     finger
    -0.08
     Orn
    -0.08
    POSITIVE LOGITS
    imo
    0.09
     tapped
    0.08
    oenix
    0.08
    emax
    0.08
    hil
    0.07
    [assembly
    0.07
    IMER
    0.07
    .Then
    0.07
    323
    0.07
    OSE
    0.07
    Activations Density 0.074%

    No Known Activations