© 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. 57290
    Prev
    Next
    INDEX
    Explanations

    screening and detection

    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
     stabil
    -0.08
     stabilize
    -0.08
     stabilization
    -0.08
     dissip
    -0.08
    /an
    -0.08
     Mixing
    -0.08
    .rm
    -0.07
     attribution
    -0.07
     dispers
    -0.07
     barric
    -0.07
    POSITIVE LOGITS
     suspicious
    0.11
     comb
    0.11
     ê²Ģ
    0.11
     detecting
    0.11
    unde
    0.10
     scanning
    0.10
    inspection
    0.10
    nds
    0.10
    -det
    0.10
    odule
    0.10
    Activations Density 0.073%

    No Known Activations