© 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. 54881
    Prev
    Next
    INDEX
    Explanations

    police reports and descriptions

    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
    rone
    -0.09
    hl
    -0.08
    rame
    -0.08
     false
    -0.08
     poor
    -0.08
    -Jan
    -0.08
     shielding
    -0.08
     falsely
    -0.08
    orm
    -0.08
     frat
    -0.08
    POSITIVE LOGITS
    ervo
    0.09
     nud
    0.08
     compact
    0.08
     digitally
    0.08
    Assert
    0.08
     Corey
    0.08
    rees
    0.08
     Found
    0.08
     similar
    0.08
     deser
    0.08
    Activations Density 0.007%

    No Known Activations