© 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. 3589
    Prev
    Next
    INDEX
    Explanations

    positive attributes or requirements

    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
    Ŀ
    -0.09
    次
    -0.09
     Kem
    -0.09
    aggregate
    -0.09
    aten
    -0.08
     borrowed
    -0.08
    onet
    -0.08
     Bil
    -0.08
    arin
    -0.08
    -case
    -0.08
    POSITIVE LOGITS
     Boeh
    0.10
    å®ī
    0.08
     tá
    0.08
     Boom
    0.08
    pta
    0.08
    visa
    0.08
    /set
    0.08
     |-
    0.08
    eso
    0.08
    earing
    0.08
    Activations Density 0.721%

    No Known Activations