© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56200
    Prev
    Next
    INDEX
    Explanations

    results of

    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
    wash
    -0.09
     notable
    -0.09
     greeting
    -0.09
     observable
    -0.08
     |_
    -0.08
    ropa
    -0.08
     familiar
    -0.08
     Lust
    -0.08
    lush
    -0.08
     terminology
    -0.08
    POSITIVE LOGITS
     sucess
    0.10
    -progress
    0.10
     grandchildren
    0.09
     efforts
    0.09
     Successfully
    0.09
     successfully
    0.08
    temps
    0.08
    idth
    0.08
    ourd
    0.08
    acent
    0.08
    Activations Density 0.111%

    No Known Activations