© 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. 4716
    Prev
    Next
    INDEX
    Explanations

    vandalism and graffiti

    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
    /form
    -0.09
     geh
    -0.08
    geb
    -0.08
     held
    -0.08
     nowhere
    -0.08
     dodge
    -0.08
     slowed
    -0.08
    Trivia
    -0.08
     Held
    -0.08
     belly
    -0.07
    POSITIVE LOGITS
     vandal
    0.16
     left
    0.13
     myster
    0.12
     vandalism
    0.12
     trail
    0.12
     overnight
    0.11
     graffiti
    0.11
     marker
    0.11
     Left
    0.11
     Overnight
    0.11
    Activations Density 0.439%

    No Known Activations