© 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. 54233
    Prev
    Next
    INDEX
    Explanations

    stalking and harassment

    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
     renegot
    -0.10
     contro
    -0.09
    tal
    -0.09
     stricter
    -0.09
     breach
    -0.09
    prov
    -0.09
     tender
    -0.09
    nesty
    -0.09
    YG
    -0.09
    centage
    -0.09
    POSITIVE LOGITS
     besie
    0.10
     omnip
    0.10
     harassed
    0.09
     torment
    0.09
     Track
    0.08
    /cop
    0.08
     track
    0.08
     trailed
    0.08
     spies
    0.08
    lyn
    0.08
    Activations Density 0.042%

    No Known Activations