© 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. 54164
    Prev
    Next
    INDEX
    Explanations

    violates rules and rights

    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
     Mang
    -0.10
     Grim
    -0.10
     Gri
    -0.09
     Spir
    -0.09
     Robot
    -0.09
    aign
    -0.09
     Atl
    -0.09
     ATL
    -0.09
    Trigger
    -0.09
     dyst
    -0.09
    POSITIVE LOGITS
    aura
    0.08
    akk
    0.08
    odi
    0.08
    away
    0.07
    awai
    0.07
    lace
    0.07
     Shirt
    0.07
    awei
    0.07
    ething
    0.07
    rad
    0.07
    Activations Density 0.003%

    No Known Activations