© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    Harry Styles, actual, degenerate

    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
    ude
    -0.08
     Et
    -0.07
    usu
    -0.07
     Eph
    -0.07
     Weed
    -0.07
    Ly
    -0.06
    SEC
    -0.06
    anness
    -0.06
    gren
    -0.06
     Monica
    -0.06
    POSITIVE LOGITS
    FU
    0.10
    erna
    0.10
    aber
    0.09
    isto
    0.09
     kms
    0.09
    dana
    0.09
    oggled
    0.09
    /client
    0.09
     Walters
    0.09
    áo
    0.09
    Activations Density 0.974%

    No Known Activations