© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115107
    Prev
    Next
    INDEX
    Explanations

    intrusion and invasion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     palm
    -0.08
     provid
    -0.06
     provision
    -0.06
    cel
    -0.06
     cooperative
    -0.06
    hoff
    -0.06
    (Source
    -0.06
     Bass
    -0.06
     urging
    -0.06
    585
    -0.06
    POSITIVE LOGITS
     intrusion
    0.33
     intr
    0.28
     intrusive
    0.24
     invasion
    0.24
     trespass
    0.23
     invading
    0.23
    intr
    0.23
     interruption
    0.23
     invade
    0.22
     Intr
    0.22
    Activations Density 0.088%

    No Known Activations