© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15429
    Prev
    Next
    INDEX
    Explanations

    say "consent"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kills
    -17.63
    CString
    -17.00
    烟囱
    -16.25
    _internal
    -16.13
    <tag
    -15.94
    umeric
    -15.56
    椒
    -15.44
    _dense
    -15.38
     internal
    -15.13
    keleton
    -15.06
    POSITIVE LOGITS
     Consent
    24.25
    cons
    23.38
    Cons
    22.75
     consent
    22.75
    -cons
    22.38
     consenting
    22.00
     cons
    21.25
    .Cons
    20.75
    自愿
    20.00
     Cons
    19.00
    Activations Density 0.109%

    No Known Activations