© 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. 55358
    Prev
    Next
    INDEX
    Explanations

    On August 2, February 6, January 5

    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
    rush
    -0.11
     downwards
    -0.10
     authorised
    -0.10
    fuse
    -0.09
    qid
    -0.09
    aset
    -0.09
     Wedding
    -0.09
    emy
    -0.09
    agrid
    -0.09
     Ky
    -0.09
    POSITIVE LOGITS
     sometime
    0.08
     resource
    0.08
    aug
    0.07
     previous
    0.07
     weight
    0.07
     deeper
    0.07
     intermediate
    0.07
     uns
    0.07
    uns
    0.07
     dearly
    0.07
    Activations Density 0.003%

    No Known Activations