© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 53807
    Prev
    Next
    INDEX
    Explanations

    vocal-auditory or F.2d

    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
    Negative Logits
     Sutton
    -0.09
     PROT
    -0.07
     act
    -0.07
     Ant
    -0.07
    æŁ
    -0.07
    Hot
    -0.07
     coun
    -0.07
    =False
    -0.07
    PATH
    -0.07
     Ne
    -0.07
    POSITIVE LOGITS
     rede
    0.10
    WND
    0.10
    tron
    0.09
    OWER
    0.09
     Spieler
    0.09
     Saying
    0.09
    azo
    0.09
     Desde
    0.08
    iar
    0.08
     menn
    0.08
    Activations Density 0.005%

    No Known Activations