© 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. 15779
    Prev
    Next
    INDEX
    Explanations

    say "reference"

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

    No Comments

    Negative Logits
     podcasts
    -16.38
     retaliation
    -15.31
     Podcast
    -14.50
    代言
    -14.38
     payloads
    -14.13
    /svg
    -14.13
     Porno
    -14.06
     recounts
    -13.94
     podcast
    -13.81
     Payload
    -13.81
    POSITIVE LOGITS
    参考
    37.25
     reference
    36.50
     Reference
    34.50
    reference
    33.50
    Reference
    33.25
    getReference
    32.00
    .reference
    31.13
    _REFERENCE
    30.25
    .Reference
    30.13
    _reference
    30.00
    Activations Density 0.145%

    No Known Activations