© 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. 56527
    Prev
    Next
    INDEX
    Explanations

    noise reduction

    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
    enie
    -0.10
     Casc
    -0.09
    amina
    -0.09
    atively
    -0.09
    >|
    -0.09
     Rece
    -0.09
     Hague
    -0.08
    ixon
    -0.08
    .saved
    -0.08
    lijah
    -0.08
    POSITIVE LOGITS
    alk
    0.09
    Ùī
    0.09
     scramble
    0.09
     Lux
    0.09
    berger
    0.09
    /Add
    0.08
    ç«ł
    0.08
     Making
    0.08
    Strength
    0.08
     rude
    0.08
    Activations Density 0.007%

    No Known Activations