© 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. 432
    Prev
    Next
    INDEX
    Explanations

    Washington State

    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
    _sz
    -0.10
    alis
    -0.10
    iez
    -0.10
    .hh
    -0.09
     frais
    -0.09
    vc
    -0.09
    ometimes
    -0.09
     "\(
    -0.09
    croft
    -0.09
    COR
    -0.09
    POSITIVE LOGITS
     devast
    0.08
     Gentle
    0.07
    ritic
    0.07
    524
    0.06
     mand
    0.06
    åĬ¨çĶŁæĪIJ
    0.06
     Outstanding
    0.06
    illusion
    0.06
    arih
    0.06
     Trem
    0.06
    Activations Density 2.516%

    No Known Activations