© 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. 57186
    Prev
    Next
    INDEX
    Explanations

    witnesses seeing or noticing events

    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
     tuning
    -0.09
     Sample
    -0.08
    ait
    -0.07
     trial
    -0.07
    priv
    -0.07
    cp
    -0.07
     ACK
    -0.07
    /head
    -0.07
     recovered
    -0.07
    coe
    -0.07
    POSITIVE LOGITS
     near
    0.10
    arias
    0.10
    swer
    0.10
     Budd
    0.10
    rene
    0.09
    edException
    0.09
     nab
    0.09
    /Common
    0.09
     indirectly
    0.09
    tery
    0.09
    Activations Density 0.009%

    No Known Activations